From 26a74368bccd013718b5757a8b9351e911e220a2 Mon Sep 17 00:00:00 2001 From: Harley Turan Date: Thu, 7 Nov 2024 11:20:47 +0000 Subject: [PATCH 1/2] Update formatting of schemas, remove image field from text-gen, remove lang from whisper --- bin/fetch-ai-models.js | 2 +- .../workers-ai-models/bart-large-cnn.json | 49 +- .../workers-ai-models/bge-base-en-v1.5.json | 83 +++- .../workers-ai-models/bge-large-en-v1.5.json | 83 +++- .../workers-ai-models/bge-small-en-v1.5.json | 83 +++- .../deepseek-coder-6.7b-base-awq.json | 384 +++++++++++++++- .../deepseek-coder-6.7b-instruct-awq.json | 384 +++++++++++++++- .../deepseek-math-7b-instruct.json | 388 +++++++++++++++- .../workers-ai-models/detr-resnet-50.json | 83 +++- .../discolm-german-7b-v1-awq.json | 384 +++++++++++++++- .../distilbert-sst-2-int8.json | 56 ++- .../workers-ai-models/dreamshaper-8-lcm.json | 100 ++++- .../workers-ai-models/falcon-7b-instruct.json | 384 +++++++++++++++- .../workers-ai-models/flux-1-schnell.json | 83 ++-- .../workers-ai-models/gemma-2b-it-lora.json | 384 +++++++++++++++- .../workers-ai-models/gemma-7b-it-lora.json | 384 +++++++++++++++- .../workers-ai-models/gemma-7b-it.json | 404 ++++++++++++++++- .../hermes-2-pro-mistral-7b.json | 388 +++++++++++++++- .../llama-2-13b-chat-awq.json | 384 +++++++++++++++- .../llama-2-7b-chat-fp16.json | 388 +++++++++++++++- .../llama-2-7b-chat-hf-lora.json | 384 +++++++++++++++- .../llama-2-7b-chat-int8.json | 375 +++++++++++++++- .../llama-3-8b-instruct-awq.json | 388 +++++++++++++++- .../llama-3-8b-instruct.json | 388 +++++++++++++++- .../llama-3.1-8b-instruct-awq.json | 384 +++++++++++++++- .../llama-3.1-8b-instruct-fp8.json | 384 +++++++++++++++- .../llama-3.1-8b-instruct.json | 384 +++++++++++++++- .../llama-3.2-11b-vision-instruct.json | 418 +++++++++++++++++- .../llama-3.2-1b-instruct.json | 384 +++++++++++++++- .../llama-3.2-3b-instruct.json | 384 +++++++++++++++- .../workers-ai-models/llamaguard-7b-awq.json | 380 +++++++++++++++- .../workers-ai-models/llava-1.5-7b-hf.json | 82 +++- .../workers-ai-models/m2m100-1.2b.json | 66 ++- .../meta-llama-3-8b-instruct.json | 375 +++++++++++++++- .../mistral-7b-instruct-v0.1-awq.json | 384 +++++++++++++++- .../mistral-7b-instruct-v0.1.json | 388 +++++++++++++++- .../mistral-7b-instruct-v0.2-lora.json | 384 +++++++++++++++- .../mistral-7b-instruct-v0.2.json | 400 ++++++++++++++++- .../neural-chat-7b-v3-1-awq.json | 380 +++++++++++++++- .../workers-ai-models/openchat-3.5-0106.json | 384 +++++++++++++++- .../openhermes-2.5-mistral-7b-awq.json | 380 +++++++++++++++- src/content/workers-ai-models/phi-2.json | 384 +++++++++++++++- .../workers-ai-models/qwen1.5-0.5b-chat.json | 384 +++++++++++++++- .../workers-ai-models/qwen1.5-1.8b-chat.json | 384 +++++++++++++++- .../qwen1.5-14b-chat-awq.json | 384 +++++++++++++++- .../qwen1.5-7b-chat-awq.json | 384 +++++++++++++++- src/content/workers-ai-models/resnet-50.json | 67 ++- .../workers-ai-models/sqlcoder-7b-2.json | 388 +++++++++++++++- .../stable-diffusion-v1-5-img2img.json | 104 ++++- .../stable-diffusion-v1-5-inpainting.json | 104 ++++- .../stable-diffusion-xl-base-1.0.json | 104 ++++- .../stable-diffusion-xl-lightning.json | 100 ++++- .../starling-lm-7b-beta.json | 396 ++++++++++++++++- .../tinyllama-1.1b-chat-v1.0.json | 384 +++++++++++++++- .../uform-gen2-qwen-500m.json | 86 +++- .../una-cybertron-7b-v2-bf16.json | 380 +++++++++++++++- .../workers-ai-models/whisper-tiny-en.json | 79 +++- src/content/workers-ai-models/whisper.json | 87 +++- .../workers-ai-models/zephyr-7b-beta-awq.json | 384 +++++++++++++++- 59 files changed, 16841 insertions(+), 96 deletions(-) diff --git a/bin/fetch-ai-models.js b/bin/fetch-ai-models.js index 0840a0750239ca8..50e4593bcb1fe75 100644 --- a/bin/fetch-ai-models.js +++ b/bin/fetch-ai-models.js @@ -7,7 +7,7 @@ fetch("https://ai.cloudflare.com/api/models") const fileName = model.name.split("/")[2]; fs.writeFileSync( `./src/content/workers-ai-models/${fileName}.json`, - JSON.stringify(model), + JSON.stringify(model, null, 4), "utf-8", ); }); diff --git a/src/content/workers-ai-models/bart-large-cnn.json b/src/content/workers-ai-models/bart-large-cnn.json index 04fe276781bc0ba..3662df67b152910 100644 --- a/src/content/workers-ai-models/bart-large-cnn.json +++ b/src/content/workers-ai-models/bart-large-cnn.json @@ -1 +1,48 @@ -{"id":"19bd38eb-bcda-4e53-bec2-704b4689b43a","source":1,"name":"@cf/facebook/bart-large-cnn","description":"BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. You can use this model for text summarization.","task":{"id":"6f4e65d8-da0f-40d2-9aa4-db582a5a04fd","name":"Summarization","description":"Summarization is the task of producing a shorter version of a document while preserving its important information. Some models can extract text from the original input, while other models can generate entirely new text."},"tags":[],"properties":[{"property_id":"beta","value":"true"}],"schema":{"input":{"type":"object","properties":{"input_text":{"type":"string","minLength":1,"description":"The text that you want the model to summarize"},"max_length":{"type":"integer","default":1024,"description":"The maximum length of the generated summary in tokens"}},"required":["input_text"]},"output":{"type":"object","contentType":"application/json","properties":{"summary":{"type":"string","description":"The summarized version of the input text"}}}}} \ No newline at end of file +{ + "id": "19bd38eb-bcda-4e53-bec2-704b4689b43a", + "source": 1, + "name": "@cf/facebook/bart-large-cnn", + "description": "BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. You can use this model for text summarization.", + "task": { + "id": "6f4e65d8-da0f-40d2-9aa4-db582a5a04fd", + "name": "Summarization", + "description": "Summarization is the task of producing a shorter version of a document while preserving its important information. Some models can extract text from the original input, while other models can generate entirely new text." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + } + ], + "schema": { + "input": { + "type": "object", + "properties": { + "input_text": { + "type": "string", + "minLength": 1, + "description": "The text that you want the model to summarize" + }, + "max_length": { + "type": "integer", + "default": 1024, + "description": "The maximum length of the generated summary in tokens" + } + }, + "required": [ + "input_text" + ] + }, + "output": { + "type": "object", + "contentType": "application/json", + "properties": { + "summary": { + "type": "string", + "description": "The summarized version of the input text" + } + } + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/bge-base-en-v1.5.json b/src/content/workers-ai-models/bge-base-en-v1.5.json index a125847de253801..e390b71f8ebc606 100644 --- a/src/content/workers-ai-models/bge-base-en-v1.5.json +++ b/src/content/workers-ai-models/bge-base-en-v1.5.json @@ -1 +1,82 @@ -{"id":"429b9e8b-d99e-44de-91ad-706cf8183658","source":1,"name":"@cf/baai/bge-base-en-v1.5","description":"BAAI general embedding (bge) models transform any given text into a compact vector","task":{"id":"0137cdcf-162a-4108-94f2-1ca59e8c65ee","name":"Text Embeddings","description":"Feature extraction models transform raw data into numerical features that can be processed while preserving the information in the original dataset. These models are ideal as part of building vector search applications or Retrieval Augmented Generation workflows with Large Language Models (LLM)."},"tags":[],"properties":[{"property_id":"beta","value":"false"},{"property_id":"info","value":"https://huggingface.co/BAAI/bge-base-en-v1.5"},{"property_id":"max_input_tokens","value":"512"},{"property_id":"output_dimensions","value":"768"}],"schema":{"input":{"type":"object","properties":{"text":{"oneOf":[{"type":"string","description":"The text to embed","minLength":1},{"type":"array","description":"Batch of text values to embed","items":{"type":"string","description":"The text to embed","minLength":1},"maxItems":100}]}},"required":["text"]},"output":{"type":"object","contentType":"application/json","properties":{"shape":{"type":"array","items":{"type":"number"}},"data":{"type":"array","description":"Embeddings of the requested text values","items":{"type":"array","description":"Floating point embedding representation shaped by the embedding model","items":{"type":"number"}}}}}}} \ No newline at end of file +{ + "id": "429b9e8b-d99e-44de-91ad-706cf8183658", + "source": 1, + "name": "@cf/baai/bge-base-en-v1.5", + "description": "BAAI general embedding (bge) models transform any given text into a compact vector", + "task": { + "id": "0137cdcf-162a-4108-94f2-1ca59e8c65ee", + "name": "Text Embeddings", + "description": "Feature extraction models transform raw data into numerical features that can be processed while preserving the information in the original dataset. These models are ideal as part of building vector search applications or Retrieval Augmented Generation workflows with Large Language Models (LLM)." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "false" + }, + { + "property_id": "info", + "value": "https://huggingface.co/BAAI/bge-base-en-v1.5" + }, + { + "property_id": "max_input_tokens", + "value": "512" + }, + { + "property_id": "output_dimensions", + "value": "768" + } + ], + "schema": { + "input": { + "type": "object", + "properties": { + "text": { + "oneOf": [ + { + "type": "string", + "description": "The text to embed", + "minLength": 1 + }, + { + "type": "array", + "description": "Batch of text values to embed", + "items": { + "type": "string", + "description": "The text to embed", + "minLength": 1 + }, + "maxItems": 100 + } + ] + } + }, + "required": [ + "text" + ] + }, + "output": { + "type": "object", + "contentType": "application/json", + "properties": { + "shape": { + "type": "array", + "items": { + "type": "number" + } + }, + "data": { + "type": "array", + "description": "Embeddings of the requested text values", + "items": { + "type": "array", + "description": "Floating point embedding representation shaped by the embedding model", + "items": { + "type": "number" + } + } + } + } + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/bge-large-en-v1.5.json b/src/content/workers-ai-models/bge-large-en-v1.5.json index b5823393ee6267d..48d3765f20c2e92 100644 --- a/src/content/workers-ai-models/bge-large-en-v1.5.json +++ b/src/content/workers-ai-models/bge-large-en-v1.5.json @@ -1 +1,82 @@ -{"id":"01bc2fb0-4bca-4598-b985-d2584a3f46c0","source":1,"name":"@cf/baai/bge-large-en-v1.5","description":"BAAI general embedding (bge) models transform any given text into a compact vector","task":{"id":"0137cdcf-162a-4108-94f2-1ca59e8c65ee","name":"Text Embeddings","description":"Feature extraction models transform raw data into numerical features that can be processed while preserving the information in the original dataset. These models are ideal as part of building vector search applications or Retrieval Augmented Generation workflows with Large Language Models (LLM)."},"tags":[],"properties":[{"property_id":"beta","value":"false"},{"property_id":"info","value":"https://huggingface.co/BAAI/bge-base-en-v1.5"},{"property_id":"max_input_tokens","value":"512"},{"property_id":"output_dimensions","value":"1024"}],"schema":{"input":{"type":"object","properties":{"text":{"oneOf":[{"type":"string","description":"The text to embed","minLength":1},{"type":"array","description":"Batch of text values to embed","items":{"type":"string","description":"The text to embed","minLength":1},"maxItems":100}]}},"required":["text"]},"output":{"type":"object","contentType":"application/json","properties":{"shape":{"type":"array","items":{"type":"number"}},"data":{"type":"array","description":"Embeddings of the requested text values","items":{"type":"array","description":"Floating point embedding representation shaped by the embedding model","items":{"type":"number"}}}}}}} \ No newline at end of file +{ + "id": "01bc2fb0-4bca-4598-b985-d2584a3f46c0", + "source": 1, + "name": "@cf/baai/bge-large-en-v1.5", + "description": "BAAI general embedding (bge) models transform any given text into a compact vector", + "task": { + "id": "0137cdcf-162a-4108-94f2-1ca59e8c65ee", + "name": "Text Embeddings", + "description": "Feature extraction models transform raw data into numerical features that can be processed while preserving the information in the original dataset. These models are ideal as part of building vector search applications or Retrieval Augmented Generation workflows with Large Language Models (LLM)." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "false" + }, + { + "property_id": "info", + "value": "https://huggingface.co/BAAI/bge-base-en-v1.5" + }, + { + "property_id": "max_input_tokens", + "value": "512" + }, + { + "property_id": "output_dimensions", + "value": "1024" + } + ], + "schema": { + "input": { + "type": "object", + "properties": { + "text": { + "oneOf": [ + { + "type": "string", + "description": "The text to embed", + "minLength": 1 + }, + { + "type": "array", + "description": "Batch of text values to embed", + "items": { + "type": "string", + "description": "The text to embed", + "minLength": 1 + }, + "maxItems": 100 + } + ] + } + }, + "required": [ + "text" + ] + }, + "output": { + "type": "object", + "contentType": "application/json", + "properties": { + "shape": { + "type": "array", + "items": { + "type": "number" + } + }, + "data": { + "type": "array", + "description": "Embeddings of the requested text values", + "items": { + "type": "array", + "description": "Floating point embedding representation shaped by the embedding model", + "items": { + "type": "number" + } + } + } + } + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/bge-small-en-v1.5.json b/src/content/workers-ai-models/bge-small-en-v1.5.json index 637e4a67eba3062..62288bb2cefb9ce 100644 --- a/src/content/workers-ai-models/bge-small-en-v1.5.json +++ b/src/content/workers-ai-models/bge-small-en-v1.5.json @@ -1 +1,82 @@ -{"id":"57fbd08a-a4c4-411c-910d-b9459ff36c20","source":1,"name":"@cf/baai/bge-small-en-v1.5","description":"BAAI general embedding (bge) models transform any given text into a compact vector","task":{"id":"0137cdcf-162a-4108-94f2-1ca59e8c65ee","name":"Text Embeddings","description":"Feature extraction models transform raw data into numerical features that can be processed while preserving the information in the original dataset. These models are ideal as part of building vector search applications or Retrieval Augmented Generation workflows with Large Language Models (LLM)."},"tags":[],"properties":[{"property_id":"beta","value":"false"},{"property_id":"info","value":"https://huggingface.co/BAAI/bge-base-en-v1.5"},{"property_id":"max_input_tokens","value":"512"},{"property_id":"output_dimensions","value":"384"}],"schema":{"input":{"type":"object","properties":{"text":{"oneOf":[{"type":"string","description":"The text to embed","minLength":1},{"type":"array","description":"Batch of text values to embed","items":{"type":"string","description":"The text to embed","minLength":1},"maxItems":100}]}},"required":["text"]},"output":{"type":"object","contentType":"application/json","properties":{"shape":{"type":"array","items":{"type":"number"}},"data":{"type":"array","description":"Embeddings of the requested text values","items":{"type":"array","description":"Floating point embedding representation shaped by the embedding model","items":{"type":"number"}}}}}}} \ No newline at end of file +{ + "id": "57fbd08a-a4c4-411c-910d-b9459ff36c20", + "source": 1, + "name": "@cf/baai/bge-small-en-v1.5", + "description": "BAAI general embedding (bge) models transform any given text into a compact vector", + "task": { + "id": "0137cdcf-162a-4108-94f2-1ca59e8c65ee", + "name": "Text Embeddings", + "description": "Feature extraction models transform raw data into numerical features that can be processed while preserving the information in the original dataset. These models are ideal as part of building vector search applications or Retrieval Augmented Generation workflows with Large Language Models (LLM)." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "false" + }, + { + "property_id": "info", + "value": "https://huggingface.co/BAAI/bge-base-en-v1.5" + }, + { + "property_id": "max_input_tokens", + "value": "512" + }, + { + "property_id": "output_dimensions", + "value": "384" + } + ], + "schema": { + "input": { + "type": "object", + "properties": { + "text": { + "oneOf": [ + { + "type": "string", + "description": "The text to embed", + "minLength": 1 + }, + { + "type": "array", + "description": "Batch of text values to embed", + "items": { + "type": "string", + "description": "The text to embed", + "minLength": 1 + }, + "maxItems": 100 + } + ] + } + }, + "required": [ + "text" + ] + }, + "output": { + "type": "object", + "contentType": "application/json", + "properties": { + "shape": { + "type": "array", + "items": { + "type": "number" + } + }, + "data": { + "type": "array", + "description": "Embeddings of the requested text values", + "items": { + "type": "array", + "description": "Floating point embedding representation shaped by the embedding model", + "items": { + "type": "number" + } + } + } + } + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/deepseek-coder-6.7b-base-awq.json b/src/content/workers-ai-models/deepseek-coder-6.7b-base-awq.json index 5424414ad9d81e5..af983000fa2156a 100644 --- a/src/content/workers-ai-models/deepseek-coder-6.7b-base-awq.json +++ b/src/content/workers-ai-models/deepseek-coder-6.7b-base-awq.json @@ -1 +1,383 @@ -{"id":"7f180530-2e16-4116-9d26-f49fbed9d372","source":2,"name":"@hf/thebloke/deepseek-coder-6.7b-base-awq","description":"Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"terms","value":"https://huggingface.co/TheBloke/deepseek-coder-6.7B-base-AWQ"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "7f180530-2e16-4116-9d26-f49fbed9d372", + "source": 2, + "name": "@hf/thebloke/deepseek-coder-6.7b-base-awq", + "description": "Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "terms", + "value": "https://huggingface.co/TheBloke/deepseek-coder-6.7B-base-AWQ" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/deepseek-coder-6.7b-instruct-awq.json b/src/content/workers-ai-models/deepseek-coder-6.7b-instruct-awq.json index fa88df01b487023..fd7a49e290756bb 100644 --- a/src/content/workers-ai-models/deepseek-coder-6.7b-instruct-awq.json +++ b/src/content/workers-ai-models/deepseek-coder-6.7b-instruct-awq.json @@ -1 +1,383 @@ -{"id":"60474554-f03b-4ff4-8ecc-c1b7c71d7b29","source":2,"name":"@hf/thebloke/deepseek-coder-6.7b-instruct-awq","description":"Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"terms","value":"https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-AWQ"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "60474554-f03b-4ff4-8ecc-c1b7c71d7b29", + "source": 2, + "name": "@hf/thebloke/deepseek-coder-6.7b-instruct-awq", + "description": "Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "terms", + "value": "https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-AWQ" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/deepseek-math-7b-instruct.json b/src/content/workers-ai-models/deepseek-math-7b-instruct.json index 075e8ba810527ad..cfc32336b7b4e06 100644 --- a/src/content/workers-ai-models/deepseek-math-7b-instruct.json +++ b/src/content/workers-ai-models/deepseek-math-7b-instruct.json @@ -1 +1,387 @@ -{"id":"4c3a544e-da47-4336-9cea-c7cbfab33f16","source":1,"name":"@cf/deepseek-ai/deepseek-math-7b-instruct","description":"DeepSeekMath-Instruct 7B is a mathematically instructed tuning model derived from DeepSeekMath-Base 7B. DeepSeekMath is initialized with DeepSeek-Coder-v1.5 7B and continues pre-training on math-related tokens sourced from Common Crawl, together with natural language and code data for 500B tokens.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/deepseek-ai/deepseek-math-7b-instruct"},{"property_id":"terms","value":"https://github.com/deepseek-ai/DeepSeek-Math/blob/main/LICENSE-MODEL"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "4c3a544e-da47-4336-9cea-c7cbfab33f16", + "source": 1, + "name": "@cf/deepseek-ai/deepseek-math-7b-instruct", + "description": "DeepSeekMath-Instruct 7B is a mathematically instructed tuning model derived from DeepSeekMath-Base 7B. DeepSeekMath is initialized with DeepSeek-Coder-v1.5 7B and continues pre-training on math-related tokens sourced from Common Crawl, together with natural language and code data for 500B tokens.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/deepseek-ai/deepseek-math-7b-instruct" + }, + { + "property_id": "terms", + "value": "https://github.com/deepseek-ai/DeepSeek-Math/blob/main/LICENSE-MODEL" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/detr-resnet-50.json b/src/content/workers-ai-models/detr-resnet-50.json index 7530a2fa5fef52d..8fa290f71689434 100644 --- a/src/content/workers-ai-models/detr-resnet-50.json +++ b/src/content/workers-ai-models/detr-resnet-50.json @@ -1 +1,82 @@ -{"id":"cc34ce52-3059-415f-9a48-12aa919d37ee","source":1,"name":"@cf/facebook/detr-resnet-50","description":"DEtection TRansformer (DETR) model trained end-to-end on COCO 2017 object detection (118k annotated images).","task":{"id":"9c178979-90d9-49d8-9e2c-0f1cf01815d4","name":"Object Detection","description":"Object detection models can detect instances of objects like persons, faces, license plates, or others in an image. This task takes an image as input and returns a list of detected objects, each one containing a label, a probability score, and its surrounding box coordinates."},"tags":[],"properties":[{"property_id":"beta","value":"true"}],"schema":{"input":{"oneOf":[{"type":"string","format":"binary","description":"The image to use for detection"},{"type":"object","properties":{"image":{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255 (unsigned 8bit)"}}}}]},"output":{"type":"array","contentType":"application/json","description":"An array of detected objects within the input image","items":{"type":"object","properties":{"score":{"type":"number","description":"Confidence score indicating the likelihood that the detection is correct"},"label":{"type":"string","description":"The class label or name of the detected object"},"box":{"type":"object","description":"Coordinates defining the bounding box around the detected object","properties":{"xmin":{"type":"number","description":"The x-coordinate of the top-left corner of the bounding box"},"ymin":{"type":"number","description":"The y-coordinate of the top-left corner of the bounding box"},"xmax":{"type":"number","description":"The x-coordinate of the bottom-right corner of the bounding box"},"ymax":{"type":"number","description":"The y-coordinate of the bottom-right corner of the bounding box"}}}}}}}} \ No newline at end of file +{ + "id": "cc34ce52-3059-415f-9a48-12aa919d37ee", + "source": 1, + "name": "@cf/facebook/detr-resnet-50", + "description": "DEtection TRansformer (DETR) model trained end-to-end on COCO 2017 object detection (118k annotated images).", + "task": { + "id": "9c178979-90d9-49d8-9e2c-0f1cf01815d4", + "name": "Object Detection", + "description": "Object detection models can detect instances of objects like persons, faces, license plates, or others in an image. This task takes an image as input and returns a list of detected objects, each one containing a label, a probability score, and its surrounding box coordinates." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + } + ], + "schema": { + "input": { + "oneOf": [ + { + "type": "string", + "format": "binary", + "description": "The image to use for detection" + }, + { + "type": "object", + "properties": { + "image": { + "type": "array", + "description": "An array of integers that represent the image data constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255 (unsigned 8bit)" + } + } + } + } + ] + }, + "output": { + "type": "array", + "contentType": "application/json", + "description": "An array of detected objects within the input image", + "items": { + "type": "object", + "properties": { + "score": { + "type": "number", + "description": "Confidence score indicating the likelihood that the detection is correct" + }, + "label": { + "type": "string", + "description": "The class label or name of the detected object" + }, + "box": { + "type": "object", + "description": "Coordinates defining the bounding box around the detected object", + "properties": { + "xmin": { + "type": "number", + "description": "The x-coordinate of the top-left corner of the bounding box" + }, + "ymin": { + "type": "number", + "description": "The y-coordinate of the top-left corner of the bounding box" + }, + "xmax": { + "type": "number", + "description": "The x-coordinate of the bottom-right corner of the bounding box" + }, + "ymax": { + "type": "number", + "description": "The y-coordinate of the bottom-right corner of the bounding box" + } + } + } + } + } + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/discolm-german-7b-v1-awq.json b/src/content/workers-ai-models/discolm-german-7b-v1-awq.json index 42ab40aa5bd79a6..95032d3f89b0e75 100644 --- a/src/content/workers-ai-models/discolm-german-7b-v1-awq.json +++ b/src/content/workers-ai-models/discolm-german-7b-v1-awq.json @@ -1 +1,383 @@ -{"id":"9d2ab560-065e-4d0d-a789-d4bc7468d33e","source":1,"name":"@cf/thebloke/discolm-german-7b-v1-awq","description":"DiscoLM German 7b is a Mistral-based large language model with a focus on German-language applications. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/TheBloke/DiscoLM_German_7b_v1-AWQ"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "9d2ab560-065e-4d0d-a789-d4bc7468d33e", + "source": 1, + "name": "@cf/thebloke/discolm-german-7b-v1-awq", + "description": "DiscoLM German 7b is a Mistral-based large language model with a focus on German-language applications. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/TheBloke/DiscoLM_German_7b_v1-AWQ" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/distilbert-sst-2-int8.json b/src/content/workers-ai-models/distilbert-sst-2-int8.json index 716a08309066995..3450e053dc10e99 100644 --- a/src/content/workers-ai-models/distilbert-sst-2-int8.json +++ b/src/content/workers-ai-models/distilbert-sst-2-int8.json @@ -1 +1,55 @@ -{"id":"eaf31752-a074-441f-8b70-d593255d2811","source":1,"name":"@cf/huggingface/distilbert-sst-2-int8","description":"Distilled BERT model that was finetuned on SST-2 for sentiment classification","task":{"id":"19606750-23ed-4371-aab2-c20349b53a60","name":"Text Classification","description":"Sentiment analysis or text classification is a common NLP task that classifies a text input into labels or classes."},"tags":[],"properties":[{"property_id":"beta","value":"false"},{"property_id":"info","value":"https://huggingface.co/Intel/distilbert-base-uncased-finetuned-sst-2-english-int8-static"}],"schema":{"input":{"type":"object","properties":{"text":{"type":"string","minLength":1,"description":"The text that you want to classify"}},"required":["text"]},"output":{"type":"array","contentType":"application/json","description":"An array of classification results for the input text","items":{"type":"object","properties":{"score":{"type":"number","description":"Confidence score indicating the likelihood that the text belongs to the specified label"},"label":{"type":"string","description":"The classification label assigned to the text (e.g., 'POSITIVE' or 'NEGATIVE')"}}}}}} \ No newline at end of file +{ + "id": "eaf31752-a074-441f-8b70-d593255d2811", + "source": 1, + "name": "@cf/huggingface/distilbert-sst-2-int8", + "description": "Distilled BERT model that was finetuned on SST-2 for sentiment classification", + "task": { + "id": "19606750-23ed-4371-aab2-c20349b53a60", + "name": "Text Classification", + "description": "Sentiment analysis or text classification is a common NLP task that classifies a text input into labels or classes." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "false" + }, + { + "property_id": "info", + "value": "https://huggingface.co/Intel/distilbert-base-uncased-finetuned-sst-2-english-int8-static" + } + ], + "schema": { + "input": { + "type": "object", + "properties": { + "text": { + "type": "string", + "minLength": 1, + "description": "The text that you want to classify" + } + }, + "required": [ + "text" + ] + }, + "output": { + "type": "array", + "contentType": "application/json", + "description": "An array of classification results for the input text", + "items": { + "type": "object", + "properties": { + "score": { + "type": "number", + "description": "Confidence score indicating the likelihood that the text belongs to the specified label" + }, + "label": { + "type": "string", + "description": "The classification label assigned to the text (e.g., 'POSITIVE' or 'NEGATIVE')" + } + } + } + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/dreamshaper-8-lcm.json b/src/content/workers-ai-models/dreamshaper-8-lcm.json index ac6f6f406f2dc49..3bbd559e8acda23 100644 --- a/src/content/workers-ai-models/dreamshaper-8-lcm.json +++ b/src/content/workers-ai-models/dreamshaper-8-lcm.json @@ -1 +1,99 @@ -{"id":"7912c0ab-542e-44b9-b9ee-3113d226a8b5","source":1,"name":"@cf/lykon/dreamshaper-8-lcm","description":"Stable Diffusion model that has been fine-tuned to be better at photorealism without sacrificing range.","task":{"id":"3d6e1f35-341b-4915-a6c8-9a7142a9033a","name":"Text-to-Image","description":"Generates images from input text. These models can be used to generate and modify images based on text prompts."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/Lykon/DreamShaper"}],"schema":{"input":{"type":"object","properties":{"prompt":{"type":"string","minLength":1,"description":"A text description of the image you want to generate"},"negative_prompt":{"type":"string","description":"Text describing elements to avoid in the generated image"},"height":{"type":"integer","minimum":256,"maximum":2048,"description":"The height of the generated image in pixels"},"width":{"type":"integer","minimum":256,"maximum":2048,"description":"The width of the generated image in pixels"},"image":{"type":"array","description":"For use with img2img tasks. An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},"image_b64":{"type":"string","description":"For use with img2img tasks. A base64-encoded string of the input image"},"mask":{"type":"array","description":"An array representing An array of integers that represent mask image data for inpainting constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},"num_steps":{"type":"integer","default":20,"maximum":20,"description":"The number of diffusion steps; higher values can improve quality but take longer"},"strength":{"type":"number","default":1,"description":"A value between 0 and 1 indicating how strongly to apply the transformation during img2img tasks; lower values make the output closer to the input image"},"guidance":{"type":"number","default":7.5,"description":"Controls how closely the generated image should adhere to the prompt; higher values make the image more aligned with the prompt"},"seed":{"type":"integer","description":"Random seed for reproducibility of the image generation"}},"required":["prompt"]},"output":{"type":"string","contentType":"image/png","format":"binary","description":"The generated image in PNG format"}}} \ No newline at end of file +{ + "id": "7912c0ab-542e-44b9-b9ee-3113d226a8b5", + "source": 1, + "name": "@cf/lykon/dreamshaper-8-lcm", + "description": "Stable Diffusion model that has been fine-tuned to be better at photorealism without sacrificing range.", + "task": { + "id": "3d6e1f35-341b-4915-a6c8-9a7142a9033a", + "name": "Text-to-Image", + "description": "Generates images from input text. These models can be used to generate and modify images based on text prompts." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/Lykon/DreamShaper" + } + ], + "schema": { + "input": { + "type": "object", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "description": "A text description of the image you want to generate" + }, + "negative_prompt": { + "type": "string", + "description": "Text describing elements to avoid in the generated image" + }, + "height": { + "type": "integer", + "minimum": 256, + "maximum": 2048, + "description": "The height of the generated image in pixels" + }, + "width": { + "type": "integer", + "minimum": 256, + "maximum": 2048, + "description": "The width of the generated image in pixels" + }, + "image": { + "type": "array", + "description": "For use with img2img tasks. An array of integers that represent the image data constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + }, + "image_b64": { + "type": "string", + "description": "For use with img2img tasks. A base64-encoded string of the input image" + }, + "mask": { + "type": "array", + "description": "An array representing An array of integers that represent mask image data for inpainting constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + }, + "num_steps": { + "type": "integer", + "default": 20, + "maximum": 20, + "description": "The number of diffusion steps; higher values can improve quality but take longer" + }, + "strength": { + "type": "number", + "default": 1, + "description": "A value between 0 and 1 indicating how strongly to apply the transformation during img2img tasks; lower values make the output closer to the input image" + }, + "guidance": { + "type": "number", + "default": 7.5, + "description": "Controls how closely the generated image should adhere to the prompt; higher values make the image more aligned with the prompt" + }, + "seed": { + "type": "integer", + "description": "Random seed for reproducibility of the image generation" + } + }, + "required": [ + "prompt" + ] + }, + "output": { + "type": "string", + "contentType": "image/png", + "format": "binary", + "description": "The generated image in PNG format" + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/falcon-7b-instruct.json b/src/content/workers-ai-models/falcon-7b-instruct.json index eccc6713dda9134..6f3c951cbecc7fa 100644 --- a/src/content/workers-ai-models/falcon-7b-instruct.json +++ b/src/content/workers-ai-models/falcon-7b-instruct.json @@ -1 +1,383 @@ -{"id":"48dd2443-0c61-43b2-8894-22abddf1b081","source":1,"name":"@cf/tiiuae/falcon-7b-instruct","description":"Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by TII based on Falcon-7B and finetuned on a mixture of chat/instruct datasets.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/tiiuae/falcon-7b-instruct"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "48dd2443-0c61-43b2-8894-22abddf1b081", + "source": 1, + "name": "@cf/tiiuae/falcon-7b-instruct", + "description": "Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by TII based on Falcon-7B and finetuned on a mixture of chat/instruct datasets.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/tiiuae/falcon-7b-instruct" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/flux-1-schnell.json b/src/content/workers-ai-models/flux-1-schnell.json index 190c85dee915d28..60e76d2052a9164 100644 --- a/src/content/workers-ai-models/flux-1-schnell.json +++ b/src/content/workers-ai-models/flux-1-schnell.json @@ -1,42 +1,49 @@ { - "id": "9e087485-23dc-47fa-997d-f5bfafc0c7cc", - "source": 1, - "name": "@cf/black-forest-labs/flux-1-schnell", - "description": "FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. ", - "task": { - "id": "3d6e1f35-341b-4915-a6c8-9a7142a9033a", - "name": "Text-to-Image", - "description": "Generates images from input text. These models can be used to generate and modify images based on text prompts." - }, - "tags": [], - "properties": [{ "property_id": "beta", "value": "true" }], - "schema": { - "input": { - "type": "object", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "A text description of the image you want to generate" - }, - "num_steps": { - "type": "integer", - "default": 4, - "maximum": 8, - "description": "The number of diffusion steps; higher values can improve quality but take longer" - } - }, - "required": ["prompt"] + "id": "9e087485-23dc-47fa-997d-f5bfafc0c7cc", + "source": 1, + "name": "@cf/black-forest-labs/flux-1-schnell", + "description": "FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. ", + "task": { + "id": "3d6e1f35-341b-4915-a6c8-9a7142a9033a", + "name": "Text-to-Image", + "description": "Generates images from input text. These models can be used to generate and modify images based on text prompts." }, - "output": { - "type": "object", - "contentType": "application/json", - "properties": { - "image": { - "type": "string", - "description": "The generated image in Base64 format." + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + } + ], + "schema": { + "input": { + "type": "object", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "description": "A text description of the image you want to generate." + }, + "steps": { + "type": "integer", + "default": 4, + "maximum": 8, + "description": "The number of diffusion steps; higher values can improve quality but take longer." + } + }, + "required": [ + "prompt" + ] + }, + "output": { + "type": "object", + "contentType": "application/json", + "properties": { + "image": { + "type": "string", + "description": "The generated image in Base64 format." + } + } } - } } - } -} +} \ No newline at end of file diff --git a/src/content/workers-ai-models/gemma-2b-it-lora.json b/src/content/workers-ai-models/gemma-2b-it-lora.json index a11575c4b013082..1f1a17f91498533 100644 --- a/src/content/workers-ai-models/gemma-2b-it-lora.json +++ b/src/content/workers-ai-models/gemma-2b-it-lora.json @@ -1 +1,383 @@ -{"id":"e8e8abe4-a372-4c13-815f-4688ba655c8e","source":1,"name":"@cf/google/gemma-2b-it-lora","description":"This is a Gemma-2B base model that Cloudflare dedicates for inference with LoRA adapters. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"lora","value":"true"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "e8e8abe4-a372-4c13-815f-4688ba655c8e", + "source": 1, + "name": "@cf/google/gemma-2b-it-lora", + "description": "This is a Gemma-2B base model that Cloudflare dedicates for inference with LoRA adapters. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "lora", + "value": "true" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/gemma-7b-it-lora.json b/src/content/workers-ai-models/gemma-7b-it-lora.json index 7969a91624b2076..29f34f2bd9f70fd 100644 --- a/src/content/workers-ai-models/gemma-7b-it-lora.json +++ b/src/content/workers-ai-models/gemma-7b-it-lora.json @@ -1 +1,383 @@ -{"id":"337170b7-bd2f-4631-9a57-688b579cf6d3","source":1,"name":"@cf/google/gemma-7b-it-lora","description":" This is a Gemma-7B base model that Cloudflare dedicates for inference with LoRA adapters. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"lora","value":"true"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "337170b7-bd2f-4631-9a57-688b579cf6d3", + "source": 1, + "name": "@cf/google/gemma-7b-it-lora", + "description": " This is a Gemma-7B base model that Cloudflare dedicates for inference with LoRA adapters. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "lora", + "value": "true" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/gemma-7b-it.json b/src/content/workers-ai-models/gemma-7b-it.json index d249dce4ce4e1c6..de214c0928ef944 100644 --- a/src/content/workers-ai-models/gemma-7b-it.json +++ b/src/content/workers-ai-models/gemma-7b-it.json @@ -1 +1,403 @@ -{"id":"0f002249-7d86-4698-aabf-8529ed86cefb","source":2,"name":"@hf/google/gemma-7b-it","description":"Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights, pre-trained variants, and instruction-tuned variants.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://ai.google.dev/gemma/docs"},{"property_id":"lora","value":"true"},{"property_id":"max_batch_prefill_tokens","value":"2048"},{"property_id":"max_input_length","value":"1512"},{"property_id":"max_total_tokens","value":"2048"},{"property_id":"terms","value":"https://ai.google.dev/gemma/terms"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "0f002249-7d86-4698-aabf-8529ed86cefb", + "source": 2, + "name": "@hf/google/gemma-7b-it", + "description": "Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights, pre-trained variants, and instruction-tuned variants.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://ai.google.dev/gemma/docs" + }, + { + "property_id": "lora", + "value": "true" + }, + { + "property_id": "max_batch_prefill_tokens", + "value": "2048" + }, + { + "property_id": "max_input_length", + "value": "1512" + }, + { + "property_id": "max_total_tokens", + "value": "2048" + }, + { + "property_id": "terms", + "value": "https://ai.google.dev/gemma/terms" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/hermes-2-pro-mistral-7b.json b/src/content/workers-ai-models/hermes-2-pro-mistral-7b.json index a23df11939fdcb6..7aa4c4a691566a4 100644 --- a/src/content/workers-ai-models/hermes-2-pro-mistral-7b.json +++ b/src/content/workers-ai-models/hermes-2-pro-mistral-7b.json @@ -1 +1,387 @@ -{"id":"44774b85-08c8-4bb8-8d2a-b06ebc538a79","source":2,"name":"@hf/nousresearch/hermes-2-pro-mistral-7b","description":"Hermes 2 Pro on Mistral 7B is the new flagship 7B Hermes! Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"function_calling","value":"true"},{"property_id":"info","value":"https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "44774b85-08c8-4bb8-8d2a-b06ebc538a79", + "source": 2, + "name": "@hf/nousresearch/hermes-2-pro-mistral-7b", + "description": "Hermes 2 Pro on Mistral 7B is the new flagship 7B Hermes! Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "function_calling", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llama-2-13b-chat-awq.json b/src/content/workers-ai-models/llama-2-13b-chat-awq.json index b9343ac9f70bca7..a27ba94d87ce5b6 100644 --- a/src/content/workers-ai-models/llama-2-13b-chat-awq.json +++ b/src/content/workers-ai-models/llama-2-13b-chat-awq.json @@ -1 +1,383 @@ -{"id":"85c5a3c6-24b0-45e7-b23a-023182578822","source":2,"name":"@hf/thebloke/llama-2-13b-chat-awq","description":"Llama 2 13B Chat AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Llama 2 variant.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/TheBloke/Llama-2-13B-chat-AWQ"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "85c5a3c6-24b0-45e7-b23a-023182578822", + "source": 2, + "name": "@hf/thebloke/llama-2-13b-chat-awq", + "description": "Llama 2 13B Chat AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Llama 2 variant.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/TheBloke/Llama-2-13B-chat-AWQ" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llama-2-7b-chat-fp16.json b/src/content/workers-ai-models/llama-2-7b-chat-fp16.json index 87742a9687815b8..d2aa36b2a48270a 100644 --- a/src/content/workers-ai-models/llama-2-7b-chat-fp16.json +++ b/src/content/workers-ai-models/llama-2-7b-chat-fp16.json @@ -1 +1,387 @@ -{"id":"ca54bcd6-0d98-4739-9b3b-5c8b4402193d","source":1,"name":"@cf/meta/llama-2-7b-chat-fp16","description":"Full precision (fp16) generative text model with 7 billion parameters from Meta","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"false"},{"property_id":"info","value":"https://ai.meta.com/llama/"},{"property_id":"terms","value":"https://ai.meta.com/resources/models-and-libraries/llama-downloads/"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "ca54bcd6-0d98-4739-9b3b-5c8b4402193d", + "source": 1, + "name": "@cf/meta/llama-2-7b-chat-fp16", + "description": "Full precision (fp16) generative text model with 7 billion parameters from Meta", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "false" + }, + { + "property_id": "info", + "value": "https://ai.meta.com/llama/" + }, + { + "property_id": "terms", + "value": "https://ai.meta.com/resources/models-and-libraries/llama-downloads/" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llama-2-7b-chat-hf-lora.json b/src/content/workers-ai-models/llama-2-7b-chat-hf-lora.json index 9fddf3bcffe4cb4..52d2f0f2d0fa15e 100644 --- a/src/content/workers-ai-models/llama-2-7b-chat-hf-lora.json +++ b/src/content/workers-ai-models/llama-2-7b-chat-hf-lora.json @@ -1 +1,383 @@ -{"id":"7ed8d8e8-6040-4680-843a-aef402d6b013","source":1,"name":"@cf/meta-llama/llama-2-7b-chat-hf-lora","description":"This is a Llama2 base model that Cloudflare dedicated for inference with LoRA adapters. Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. ","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"lora","value":"true"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "7ed8d8e8-6040-4680-843a-aef402d6b013", + "source": 1, + "name": "@cf/meta-llama/llama-2-7b-chat-hf-lora", + "description": "This is a Llama2 base model that Cloudflare dedicated for inference with LoRA adapters. Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. ", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "lora", + "value": "true" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llama-2-7b-chat-int8.json b/src/content/workers-ai-models/llama-2-7b-chat-int8.json index d11c4b0d404586b..b74311b3ed3c3ea 100644 --- a/src/content/workers-ai-models/llama-2-7b-chat-int8.json +++ b/src/content/workers-ai-models/llama-2-7b-chat-int8.json @@ -1 +1,374 @@ -{"id":"9c95c39d-45b3-4163-9631-22f0c0dc3b14","source":1,"name":"@cf/meta/llama-2-7b-chat-int8","description":"Quantized (int8) generative text model with 7 billion parameters from Meta","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "9c95c39d-45b3-4163-9631-22f0c0dc3b14", + "source": 1, + "name": "@cf/meta/llama-2-7b-chat-int8", + "description": "Quantized (int8) generative text model with 7 billion parameters from Meta", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llama-3-8b-instruct-awq.json b/src/content/workers-ai-models/llama-3-8b-instruct-awq.json index ca6926b92788460..3326e41995be884 100644 --- a/src/content/workers-ai-models/llama-3-8b-instruct-awq.json +++ b/src/content/workers-ai-models/llama-3-8b-instruct-awq.json @@ -1 +1,387 @@ -{"id":"31097538-a3ff-4e6e-bb56-ad0e1f428b61","source":1,"name":"@cf/meta/llama-3-8b-instruct-awq","description":"Quantized (int4) generative text model with 8 billion parameters from Meta.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://llama.meta.com"},{"property_id":"terms","value":"https://llama.meta.com/llama3/license/#"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "31097538-a3ff-4e6e-bb56-ad0e1f428b61", + "source": 1, + "name": "@cf/meta/llama-3-8b-instruct-awq", + "description": "Quantized (int4) generative text model with 8 billion parameters from Meta.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://llama.meta.com" + }, + { + "property_id": "terms", + "value": "https://llama.meta.com/llama3/license/#" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llama-3-8b-instruct.json b/src/content/workers-ai-models/llama-3-8b-instruct.json index 8a2d8a16e241c83..3a6d40d0ab5b799 100644 --- a/src/content/workers-ai-models/llama-3-8b-instruct.json +++ b/src/content/workers-ai-models/llama-3-8b-instruct.json @@ -1 +1,387 @@ -{"id":"e11d8f45-7b08-499a-9eeb-71d4d3c8cbf9","source":1,"name":"@cf/meta/llama-3-8b-instruct","description":"Generation over generation, Meta Llama 3 demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://llama.meta.com"},{"property_id":"terms","value":"https://llama.meta.com/llama3/license/#"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "e11d8f45-7b08-499a-9eeb-71d4d3c8cbf9", + "source": 1, + "name": "@cf/meta/llama-3-8b-instruct", + "description": "Generation over generation, Meta Llama 3 demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://llama.meta.com" + }, + { + "property_id": "terms", + "value": "https://llama.meta.com/llama3/license/#" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llama-3.1-8b-instruct-awq.json b/src/content/workers-ai-models/llama-3.1-8b-instruct-awq.json index ea29ac2f1619d3a..83907c5c5123125 100644 --- a/src/content/workers-ai-models/llama-3.1-8b-instruct-awq.json +++ b/src/content/workers-ai-models/llama-3.1-8b-instruct-awq.json @@ -1 +1,383 @@ -{"id":"3dcb4f2d-26a8-412b-b6e3-2a368beff66b","source":1,"name":"@cf/meta/llama-3.1-8b-instruct-awq","description":"Quantized (int4) generative text model with 8 billion parameters from Meta.\n","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"terms","value":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "3dcb4f2d-26a8-412b-b6e3-2a368beff66b", + "source": 1, + "name": "@cf/meta/llama-3.1-8b-instruct-awq", + "description": "Quantized (int4) generative text model with 8 billion parameters from Meta.\n", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "terms", + "value": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llama-3.1-8b-instruct-fp8.json b/src/content/workers-ai-models/llama-3.1-8b-instruct-fp8.json index 0d84c93a2c5c797..0bdfbc95fb2ecb8 100644 --- a/src/content/workers-ai-models/llama-3.1-8b-instruct-fp8.json +++ b/src/content/workers-ai-models/llama-3.1-8b-instruct-fp8.json @@ -1 +1,383 @@ -{"id":"9b9c87c6-d4b7-494c-b177-87feab5904db","source":1,"name":"@cf/meta/llama-3.1-8b-instruct-fp8","description":"Llama 3.1 8B quantized to FP8 precision","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"terms","value":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "9b9c87c6-d4b7-494c-b177-87feab5904db", + "source": 1, + "name": "@cf/meta/llama-3.1-8b-instruct-fp8", + "description": "Llama 3.1 8B quantized to FP8 precision", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "terms", + "value": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llama-3.1-8b-instruct.json b/src/content/workers-ai-models/llama-3.1-8b-instruct.json index 68ca6008dd24339..ec4604d6761a9a0 100644 --- a/src/content/workers-ai-models/llama-3.1-8b-instruct.json +++ b/src/content/workers-ai-models/llama-3.1-8b-instruct.json @@ -1 +1,383 @@ -{"id":"41975cc2-c82e-4e98-b7b8-88ffb186a545","source":1,"name":"@cf/meta/llama-3.1-8b-instruct","description":"The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models. The Llama 3.1 instruction tuned text only models are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"terms","value":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "41975cc2-c82e-4e98-b7b8-88ffb186a545", + "source": 1, + "name": "@cf/meta/llama-3.1-8b-instruct", + "description": "The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models. The Llama 3.1 instruction tuned text only models are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "terms", + "value": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llama-3.2-11b-vision-instruct.json b/src/content/workers-ai-models/llama-3.2-11b-vision-instruct.json index 729eb15662e3a77..274629694bea7b3 100644 --- a/src/content/workers-ai-models/llama-3.2-11b-vision-instruct.json +++ b/src/content/workers-ai-models/llama-3.2-11b-vision-instruct.json @@ -1 +1,417 @@ -{"id":"2cbc033b-ded8-4e02-bbb2-47cf05d5cfe5","source":1,"name":"@cf/meta/llama-3.2-11b-vision-instruct","description":" The Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"terms","value":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "2cbc033b-ded8-4e02-bbb2-47cf05d5cfe5", + "source": 1, + "name": "@cf/meta/llama-3.2-11b-vision-instruct", + "description": " The Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "terms", + "value": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "image": { + "oneOf": [ + { + "type": "array", + "description": "An array of integers that represent the image data constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + }, + { + "type": "string", + "format": "binary", + "description": "Binary string representing the image contents." + } + ] + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "image": { + "oneOf": [ + { + "type": "array", + "description": "An array of integers that represent the image data constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + }, + { + "type": "string", + "format": "binary", + "description": "Binary string representing the image contents." + } + ] + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llama-3.2-1b-instruct.json b/src/content/workers-ai-models/llama-3.2-1b-instruct.json index 5c1ad3c7b0a42e5..3ffc3faf072fd15 100644 --- a/src/content/workers-ai-models/llama-3.2-1b-instruct.json +++ b/src/content/workers-ai-models/llama-3.2-1b-instruct.json @@ -1 +1,383 @@ -{"id":"906a57fd-b018-4d6c-a43e-a296d4cc5839","source":1,"name":"@cf/meta/llama-3.2-1b-instruct","description":"The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"terms","value":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "906a57fd-b018-4d6c-a43e-a296d4cc5839", + "source": 1, + "name": "@cf/meta/llama-3.2-1b-instruct", + "description": "The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "terms", + "value": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llama-3.2-3b-instruct.json b/src/content/workers-ai-models/llama-3.2-3b-instruct.json index e00accd4f78df9d..0b10dbe0ff6cc6a 100644 --- a/src/content/workers-ai-models/llama-3.2-3b-instruct.json +++ b/src/content/workers-ai-models/llama-3.2-3b-instruct.json @@ -1 +1,383 @@ -{"id":"d9dc8363-66f4-4bb0-8641-464ee7bfc131","source":1,"name":"@cf/meta/llama-3.2-3b-instruct","description":"The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"terms","value":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "d9dc8363-66f4-4bb0-8641-464ee7bfc131", + "source": 1, + "name": "@cf/meta/llama-3.2-3b-instruct", + "description": "The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "terms", + "value": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llamaguard-7b-awq.json b/src/content/workers-ai-models/llamaguard-7b-awq.json index 8dfb5dfc26ff6af..5358509863c92e6 100644 --- a/src/content/workers-ai-models/llamaguard-7b-awq.json +++ b/src/content/workers-ai-models/llamaguard-7b-awq.json @@ -1 +1,379 @@ -{"id":"d9b7a55c-cefa-4208-8ab3-11497a2b046c","source":2,"name":"@hf/thebloke/llamaguard-7b-awq","description":"Llama Guard is a model for classifying the safety of LLM prompts and responses, using a taxonomy of safety risks.\n","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "d9b7a55c-cefa-4208-8ab3-11497a2b046c", + "source": 2, + "name": "@hf/thebloke/llamaguard-7b-awq", + "description": "Llama Guard is a model for classifying the safety of LLM prompts and responses, using a taxonomy of safety risks.\n", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llava-1.5-7b-hf.json b/src/content/workers-ai-models/llava-1.5-7b-hf.json index e6f09819a0c8113..9ede5fbeebc0b37 100644 --- a/src/content/workers-ai-models/llava-1.5-7b-hf.json +++ b/src/content/workers-ai-models/llava-1.5-7b-hf.json @@ -1 +1,81 @@ -{"id":"af274959-cb47-4ba8-9d8e-5a0a58b6b402","source":1,"name":"@cf/llava-hf/llava-1.5-7b-hf","description":"LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.","task":{"id":"882a91d1-c331-4eec-bdad-834c919942a8","name":"Image-to-Text","description":"Image to text models output a text from a given image. Image captioning or optical character recognition can be considered as the most common applications of image to text."},"tags":[],"properties":[{"property_id":"beta","value":"true"}],"schema":{"input":{"oneOf":[{"type":"string","format":"binary","description":"Binary string representing the image contents."},{"type":"object","properties":{"temperature":{"type":"number","description":"Controls the randomness of the output; higher values produce more random results."},"prompt":{"type":"string","description":"The input text prompt for the model to generate a response."},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"max_tokens":{"type":"integer","default":512,"description":"The maximum number of tokens to generate in the response."}},"required":["image"]}]},"output":{"type":"object","contentType":"application/json","properties":{"description":{"type":"string"}}}}} \ No newline at end of file +{ + "id": "af274959-cb47-4ba8-9d8e-5a0a58b6b402", + "source": 1, + "name": "@cf/llava-hf/llava-1.5-7b-hf", + "description": "LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.", + "task": { + "id": "882a91d1-c331-4eec-bdad-834c919942a8", + "name": "Image-to-Text", + "description": "Image to text models output a text from a given image. Image captioning or optical character recognition can be considered as the most common applications of image to text." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + } + ], + "schema": { + "input": { + "oneOf": [ + { + "type": "string", + "format": "binary", + "description": "Binary string representing the image contents." + }, + { + "type": "object", + "properties": { + "temperature": { + "type": "number", + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "prompt": { + "type": "string", + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "image": { + "oneOf": [ + { + "type": "array", + "description": "An array of integers that represent the image data constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + }, + { + "type": "string", + "format": "binary", + "description": "Binary string representing the image contents." + } + ] + }, + "max_tokens": { + "type": "integer", + "default": 512, + "description": "The maximum number of tokens to generate in the response." + } + }, + "required": [ + "image" + ] + } + ] + }, + "output": { + "type": "object", + "contentType": "application/json", + "properties": { + "description": { + "type": "string" + } + } + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/m2m100-1.2b.json b/src/content/workers-ai-models/m2m100-1.2b.json index 12a362748e18ff4..85196a640032e3d 100644 --- a/src/content/workers-ai-models/m2m100-1.2b.json +++ b/src/content/workers-ai-models/m2m100-1.2b.json @@ -1 +1,65 @@ -{"id":"617e7ec3-bf8d-4088-a863-4f89582d91b5","source":1,"name":"@cf/meta/m2m100-1.2b","description":"Multilingual encoder-decoder (seq-to-seq) model trained for Many-to-Many multilingual translation","task":{"id":"f57d07cb-9087-487a-bbbf-bc3e17fecc4b","name":"Translation","description":"Translation models convert a sequence of text from one language to another."},"tags":[],"properties":[{"property_id":"beta","value":"false"},{"property_id":"info","value":"https://github.com/facebookresearch/fairseq/tree/main/examples/m2m_100"},{"property_id":"languages","value":"english, chinese, french, spanish, arabic, russian, german, japanese, portuguese, hindi"},{"property_id":"terms","value":"https://github.com/facebookresearch/fairseq/blob/main/LICENSE"}],"schema":{"input":{"type":"object","properties":{"text":{"type":"string","minLength":1,"description":"The text to be translated"},"source_lang":{"type":"string","default":"en","description":"The language code of the source text (e.g., 'en' for English). Defaults to 'en' if not specified"},"target_lang":{"type":"string","description":"The language code to translate the text into (e.g., 'es' for Spanish)"}},"required":["text","target_lang"]},"output":{"type":"object","contentType":"application/json","properties":{"translated_text":{"type":"string","description":"The translated text in the target language"}}}}} \ No newline at end of file +{ + "id": "617e7ec3-bf8d-4088-a863-4f89582d91b5", + "source": 1, + "name": "@cf/meta/m2m100-1.2b", + "description": "Multilingual encoder-decoder (seq-to-seq) model trained for Many-to-Many multilingual translation", + "task": { + "id": "f57d07cb-9087-487a-bbbf-bc3e17fecc4b", + "name": "Translation", + "description": "Translation models convert a sequence of text from one language to another." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "false" + }, + { + "property_id": "info", + "value": "https://github.com/facebookresearch/fairseq/tree/main/examples/m2m_100" + }, + { + "property_id": "languages", + "value": "english, chinese, french, spanish, arabic, russian, german, japanese, portuguese, hindi" + }, + { + "property_id": "terms", + "value": "https://github.com/facebookresearch/fairseq/blob/main/LICENSE" + } + ], + "schema": { + "input": { + "type": "object", + "properties": { + "text": { + "type": "string", + "minLength": 1, + "description": "The text to be translated" + }, + "source_lang": { + "type": "string", + "default": "en", + "description": "The language code of the source text (e.g., 'en' for English). Defaults to 'en' if not specified" + }, + "target_lang": { + "type": "string", + "description": "The language code to translate the text into (e.g., 'es' for Spanish)" + } + }, + "required": [ + "text", + "target_lang" + ] + }, + "output": { + "type": "object", + "contentType": "application/json", + "properties": { + "translated_text": { + "type": "string", + "description": "The translated text in the target language" + } + } + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/meta-llama-3-8b-instruct.json b/src/content/workers-ai-models/meta-llama-3-8b-instruct.json index b27de91cf801ad6..508f013bb789a73 100644 --- a/src/content/workers-ai-models/meta-llama-3-8b-instruct.json +++ b/src/content/workers-ai-models/meta-llama-3-8b-instruct.json @@ -1 +1,374 @@ -{"id":"1a7b6ad6-9987-4bd3-a329-20ee8de93296","source":2,"name":"@hf/meta-llama/meta-llama-3-8b-instruct","description":"Generation over generation, Meta Llama 3 demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.\t","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "1a7b6ad6-9987-4bd3-a329-20ee8de93296", + "source": 2, + "name": "@hf/meta-llama/meta-llama-3-8b-instruct", + "description": "Generation over generation, Meta Llama 3 demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.\t", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/mistral-7b-instruct-v0.1-awq.json b/src/content/workers-ai-models/mistral-7b-instruct-v0.1-awq.json index 3d7db3852e325a1..2493b2edfa182ec 100644 --- a/src/content/workers-ai-models/mistral-7b-instruct-v0.1-awq.json +++ b/src/content/workers-ai-models/mistral-7b-instruct-v0.1-awq.json @@ -1 +1,383 @@ -{"id":"980ec5e9-33c2-483a-a2d8-cd092fdf273f","source":2,"name":"@hf/thebloke/mistral-7b-instruct-v0.1-awq","description":"Mistral 7B Instruct v0.1 AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Mistral variant.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-AWQ"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "980ec5e9-33c2-483a-a2d8-cd092fdf273f", + "source": 2, + "name": "@hf/thebloke/mistral-7b-instruct-v0.1-awq", + "description": "Mistral 7B Instruct v0.1 AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Mistral variant.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-AWQ" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/mistral-7b-instruct-v0.1.json b/src/content/workers-ai-models/mistral-7b-instruct-v0.1.json index df5ab20502e3781..673f78101bfdcdd 100644 --- a/src/content/workers-ai-models/mistral-7b-instruct-v0.1.json +++ b/src/content/workers-ai-models/mistral-7b-instruct-v0.1.json @@ -1 +1,387 @@ -{"id":"c907d0f9-d69d-4e93-b501-4daeb4fd69eb","source":1,"name":"@cf/mistral/mistral-7b-instruct-v0.1","description":"Instruct fine-tuned version of the Mistral-7b generative text model with 7 billion parameters","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"false"},{"property_id":"info","value":"https://mistral.ai/news/announcing-mistral-7b/"},{"property_id":"lora","value":"true"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "c907d0f9-d69d-4e93-b501-4daeb4fd69eb", + "source": 1, + "name": "@cf/mistral/mistral-7b-instruct-v0.1", + "description": "Instruct fine-tuned version of the Mistral-7b generative text model with 7 billion parameters", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "false" + }, + { + "property_id": "info", + "value": "https://mistral.ai/news/announcing-mistral-7b/" + }, + { + "property_id": "lora", + "value": "true" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/mistral-7b-instruct-v0.2-lora.json b/src/content/workers-ai-models/mistral-7b-instruct-v0.2-lora.json index 9ee117deb78c721..eced60504f5b11c 100644 --- a/src/content/workers-ai-models/mistral-7b-instruct-v0.2-lora.json +++ b/src/content/workers-ai-models/mistral-7b-instruct-v0.2-lora.json @@ -1 +1,383 @@ -{"id":"c58c317b-0c15-4bda-abb6-93e275f282d9","source":1,"name":"@cf/mistral/mistral-7b-instruct-v0.2-lora","description":"The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"lora","value":"true"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "c58c317b-0c15-4bda-abb6-93e275f282d9", + "source": 1, + "name": "@cf/mistral/mistral-7b-instruct-v0.2-lora", + "description": "The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "lora", + "value": "true" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/mistral-7b-instruct-v0.2.json b/src/content/workers-ai-models/mistral-7b-instruct-v0.2.json index 30a7f548ecf5c47..9af988219d67969 100644 --- a/src/content/workers-ai-models/mistral-7b-instruct-v0.2.json +++ b/src/content/workers-ai-models/mistral-7b-instruct-v0.2.json @@ -1 +1,399 @@ -{"id":"b97d7069-48d9-461c-80dd-445d20a632eb","source":2,"name":"@hf/mistral/mistral-7b-instruct-v0.2","description":"The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2. Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1: 32k context window (vs 8k context in v0.1), rope-theta = 1e6, and no Sliding-Window Attention.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2"},{"property_id":"lora","value":"true"},{"property_id":"max_batch_prefill_tokens","value":"8192"},{"property_id":"max_input_length","value":"3072"},{"property_id":"max_total_tokens","value":"4096"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "b97d7069-48d9-461c-80dd-445d20a632eb", + "source": 2, + "name": "@hf/mistral/mistral-7b-instruct-v0.2", + "description": "The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2. Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1: 32k context window (vs 8k context in v0.1), rope-theta = 1e6, and no Sliding-Window Attention.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2" + }, + { + "property_id": "lora", + "value": "true" + }, + { + "property_id": "max_batch_prefill_tokens", + "value": "8192" + }, + { + "property_id": "max_input_length", + "value": "3072" + }, + { + "property_id": "max_total_tokens", + "value": "4096" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/neural-chat-7b-v3-1-awq.json b/src/content/workers-ai-models/neural-chat-7b-v3-1-awq.json index 24d74f860caf521..a7c26f5d880acb0 100644 --- a/src/content/workers-ai-models/neural-chat-7b-v3-1-awq.json +++ b/src/content/workers-ai-models/neural-chat-7b-v3-1-awq.json @@ -1 +1,379 @@ -{"id":"d2ba5c6b-bbb7-49d6-b466-900654870cd6","source":2,"name":"@hf/thebloke/neural-chat-7b-v3-1-awq","description":"This model is a fine-tuned 7B parameter LLM on the Intel Gaudi 2 processor from the mistralai/Mistral-7B-v0.1 on the open source dataset Open-Orca/SlimOrca.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "d2ba5c6b-bbb7-49d6-b466-900654870cd6", + "source": 2, + "name": "@hf/thebloke/neural-chat-7b-v3-1-awq", + "description": "This model is a fine-tuned 7B parameter LLM on the Intel Gaudi 2 processor from the mistralai/Mistral-7B-v0.1 on the open source dataset Open-Orca/SlimOrca.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/openchat-3.5-0106.json b/src/content/workers-ai-models/openchat-3.5-0106.json index 7408bd385b72a09..d06ae2f8a09b032 100644 --- a/src/content/workers-ai-models/openchat-3.5-0106.json +++ b/src/content/workers-ai-models/openchat-3.5-0106.json @@ -1 +1,383 @@ -{"id":"081054cd-a254-4349-855e-6dc0996277fa","source":1,"name":"@cf/openchat/openchat-3.5-0106","description":"OpenChat is an innovative library of open-source language models, fine-tuned with C-RLFT - a strategy inspired by offline reinforcement learning.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/openchat/openchat-3.5-0106"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "081054cd-a254-4349-855e-6dc0996277fa", + "source": 1, + "name": "@cf/openchat/openchat-3.5-0106", + "description": "OpenChat is an innovative library of open-source language models, fine-tuned with C-RLFT - a strategy inspired by offline reinforcement learning.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/openchat/openchat-3.5-0106" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/openhermes-2.5-mistral-7b-awq.json b/src/content/workers-ai-models/openhermes-2.5-mistral-7b-awq.json index 06beab8dbd17bd6..c20787e20cb26d9 100644 --- a/src/content/workers-ai-models/openhermes-2.5-mistral-7b-awq.json +++ b/src/content/workers-ai-models/openhermes-2.5-mistral-7b-awq.json @@ -1 +1,379 @@ -{"id":"673c56cc-8553-49a1-b179-dd549ec9209a","source":2,"name":"@hf/thebloke/openhermes-2.5-mistral-7b-awq","description":"OpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "673c56cc-8553-49a1-b179-dd549ec9209a", + "source": 2, + "name": "@hf/thebloke/openhermes-2.5-mistral-7b-awq", + "description": "OpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/phi-2.json b/src/content/workers-ai-models/phi-2.json index 3085e5fac90de11..4e3f994f6fa5470 100644 --- a/src/content/workers-ai-models/phi-2.json +++ b/src/content/workers-ai-models/phi-2.json @@ -1 +1,383 @@ -{"id":"1d933df3-680f-4280-940d-da87435edb07","source":1,"name":"@cf/microsoft/phi-2","description":"Phi-2 is a Transformer-based model with a next-word prediction objective, trained on 1.4T tokens from multiple passes on a mixture of Synthetic and Web datasets for NLP and coding.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/microsoft/phi-2"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "1d933df3-680f-4280-940d-da87435edb07", + "source": 1, + "name": "@cf/microsoft/phi-2", + "description": "Phi-2 is a Transformer-based model with a next-word prediction objective, trained on 1.4T tokens from multiple passes on a mixture of Synthetic and Web datasets for NLP and coding.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/microsoft/phi-2" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/qwen1.5-0.5b-chat.json b/src/content/workers-ai-models/qwen1.5-0.5b-chat.json index f9927d8eb81a2ea..dc774a96d5bd882 100644 --- a/src/content/workers-ai-models/qwen1.5-0.5b-chat.json +++ b/src/content/workers-ai-models/qwen1.5-0.5b-chat.json @@ -1 +1,383 @@ -{"id":"f8703a00-ed54-4f98-bdc3-cd9a813286f3","source":1,"name":"@cf/qwen/qwen1.5-0.5b-chat","description":"Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/qwen/qwen1.5-0.5b-chat"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "f8703a00-ed54-4f98-bdc3-cd9a813286f3", + "source": 1, + "name": "@cf/qwen/qwen1.5-0.5b-chat", + "description": "Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/qwen/qwen1.5-0.5b-chat" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/qwen1.5-1.8b-chat.json b/src/content/workers-ai-models/qwen1.5-1.8b-chat.json index 733dccf733ec58b..9fd715d1e71e5db 100644 --- a/src/content/workers-ai-models/qwen1.5-1.8b-chat.json +++ b/src/content/workers-ai-models/qwen1.5-1.8b-chat.json @@ -1 +1,383 @@ -{"id":"3222ddb3-e211-4fd9-9a6d-79a80e47b3a6","source":1,"name":"@cf/qwen/qwen1.5-1.8b-chat","description":"Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/qwen/qwen1.5-1.8b-chat"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "3222ddb3-e211-4fd9-9a6d-79a80e47b3a6", + "source": 1, + "name": "@cf/qwen/qwen1.5-1.8b-chat", + "description": "Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/qwen/qwen1.5-1.8b-chat" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/qwen1.5-14b-chat-awq.json b/src/content/workers-ai-models/qwen1.5-14b-chat-awq.json index 3e2faafc6724ab3..711a12355962065 100644 --- a/src/content/workers-ai-models/qwen1.5-14b-chat-awq.json +++ b/src/content/workers-ai-models/qwen1.5-14b-chat-awq.json @@ -1 +1,383 @@ -{"id":"09d113a9-03c4-420e-b6f2-52ad4b3bed45","source":1,"name":"@cf/qwen/qwen1.5-14b-chat-awq","description":"Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/qwen/qwen1.5-14b-chat-awq"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "09d113a9-03c4-420e-b6f2-52ad4b3bed45", + "source": 1, + "name": "@cf/qwen/qwen1.5-14b-chat-awq", + "description": "Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/qwen/qwen1.5-14b-chat-awq" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/qwen1.5-7b-chat-awq.json b/src/content/workers-ai-models/qwen1.5-7b-chat-awq.json index cd4d94e6f06eeb7..812dc114b83f181 100644 --- a/src/content/workers-ai-models/qwen1.5-7b-chat-awq.json +++ b/src/content/workers-ai-models/qwen1.5-7b-chat-awq.json @@ -1 +1,383 @@ -{"id":"90a20ae7-7cf4-4eb3-8672-8fc4ee580635","source":1,"name":"@cf/qwen/qwen1.5-7b-chat-awq","description":"Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/qwen/qwen1.5-7b-chat-awq"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "90a20ae7-7cf4-4eb3-8672-8fc4ee580635", + "source": 1, + "name": "@cf/qwen/qwen1.5-7b-chat-awq", + "description": "Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/qwen/qwen1.5-7b-chat-awq" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/resnet-50.json b/src/content/workers-ai-models/resnet-50.json index 0a9e121faf6bb20..f0a316007770dc2 100644 --- a/src/content/workers-ai-models/resnet-50.json +++ b/src/content/workers-ai-models/resnet-50.json @@ -1 +1,66 @@ -{"id":"7f9a76e1-d120-48dd-a565-101d328bbb02","source":1,"name":"@cf/microsoft/resnet-50","description":"50 layers deep image classification CNN trained on more than 1M images from ImageNet","task":{"id":"00cd182b-bf30-4fc4-8481-84a3ab349657","name":"Image Classification","description":"Image classification models take an image input and assigns it labels or classes."},"tags":[],"properties":[{"property_id":"beta","value":"false"},{"property_id":"info","value":"https://www.microsoft.com/en-us/research/blog/microsoft-vision-model-resnet-50-combines-web-scale-data-and-multi-task-learning-to-achieve-state-of-the-art/"}],"schema":{"input":{"oneOf":[{"type":"string","format":"binary","description":"The image to classify"},{"type":"object","properties":{"image":{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255 (unsigned 8bit)"}}},"required":["image"]}]},"output":{"type":"array","contentType":"application/json","items":{"type":"object","properties":{"score":{"type":"number","description":"A confidence value, between 0 and 1, indicating how certain the model is about the predicted label"},"label":{"type":"string","description":"The predicted category or class for the input image based on analysis"}}}}}} \ No newline at end of file +{ + "id": "7f9a76e1-d120-48dd-a565-101d328bbb02", + "source": 1, + "name": "@cf/microsoft/resnet-50", + "description": "50 layers deep image classification CNN trained on more than 1M images from ImageNet", + "task": { + "id": "00cd182b-bf30-4fc4-8481-84a3ab349657", + "name": "Image Classification", + "description": "Image classification models take an image input and assigns it labels or classes." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "false" + }, + { + "property_id": "info", + "value": "https://www.microsoft.com/en-us/research/blog/microsoft-vision-model-resnet-50-combines-web-scale-data-and-multi-task-learning-to-achieve-state-of-the-art/" + } + ], + "schema": { + "input": { + "oneOf": [ + { + "type": "string", + "format": "binary", + "description": "The image to classify" + }, + { + "type": "object", + "properties": { + "image": { + "type": "array", + "description": "An array of integers that represent the image data constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255 (unsigned 8bit)" + } + } + }, + "required": [ + "image" + ] + } + ] + }, + "output": { + "type": "array", + "contentType": "application/json", + "items": { + "type": "object", + "properties": { + "score": { + "type": "number", + "description": "A confidence value, between 0 and 1, indicating how certain the model is about the predicted label" + }, + "label": { + "type": "string", + "description": "The predicted category or class for the input image based on analysis" + } + } + } + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/sqlcoder-7b-2.json b/src/content/workers-ai-models/sqlcoder-7b-2.json index 5598fd3733e0fa0..af330a2f4255cb0 100644 --- a/src/content/workers-ai-models/sqlcoder-7b-2.json +++ b/src/content/workers-ai-models/sqlcoder-7b-2.json @@ -1 +1,387 @@ -{"id":"1dc9e589-df6b-4e66-ac9f-ceff42d64983","source":1,"name":"@cf/defog/sqlcoder-7b-2","description":"This model is intended to be used by non-technical users to understand data inside their SQL databases. ","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/defog/sqlcoder-7b-2"},{"property_id":"terms","value":"https://creativecommons.org/licenses/by-sa/4.0/deed.en"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "1dc9e589-df6b-4e66-ac9f-ceff42d64983", + "source": 1, + "name": "@cf/defog/sqlcoder-7b-2", + "description": "This model is intended to be used by non-technical users to understand data inside their SQL databases. ", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/defog/sqlcoder-7b-2" + }, + { + "property_id": "terms", + "value": "https://creativecommons.org/licenses/by-sa/4.0/deed.en" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/stable-diffusion-v1-5-img2img.json b/src/content/workers-ai-models/stable-diffusion-v1-5-img2img.json index a6a2a16beaed843..b87125b25d7900e 100644 --- a/src/content/workers-ai-models/stable-diffusion-v1-5-img2img.json +++ b/src/content/workers-ai-models/stable-diffusion-v1-5-img2img.json @@ -1 +1,103 @@ -{"id":"19547f04-7a6a-4f87-bf2c-f5e32fb12dc5","source":1,"name":"@cf/runwayml/stable-diffusion-v1-5-img2img","description":"Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images. Img2img generate a new image from an input image with Stable Diffusion. ","task":{"id":"3d6e1f35-341b-4915-a6c8-9a7142a9033a","name":"Text-to-Image","description":"Generates images from input text. These models can be used to generate and modify images based on text prompts."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/runwayml/stable-diffusion-v1-5"},{"property_id":"terms","value":"https://github.com/runwayml/stable-diffusion/blob/main/LICENSE"}],"schema":{"input":{"type":"object","properties":{"prompt":{"type":"string","minLength":1,"description":"A text description of the image you want to generate"},"negative_prompt":{"type":"string","description":"Text describing elements to avoid in the generated image"},"height":{"type":"integer","minimum":256,"maximum":2048,"description":"The height of the generated image in pixels"},"width":{"type":"integer","minimum":256,"maximum":2048,"description":"The width of the generated image in pixels"},"image":{"type":"array","description":"For use with img2img tasks. An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},"image_b64":{"type":"string","description":"For use with img2img tasks. A base64-encoded string of the input image"},"mask":{"type":"array","description":"An array representing An array of integers that represent mask image data for inpainting constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},"num_steps":{"type":"integer","default":20,"maximum":20,"description":"The number of diffusion steps; higher values can improve quality but take longer"},"strength":{"type":"number","default":1,"description":"A value between 0 and 1 indicating how strongly to apply the transformation during img2img tasks; lower values make the output closer to the input image"},"guidance":{"type":"number","default":7.5,"description":"Controls how closely the generated image should adhere to the prompt; higher values make the image more aligned with the prompt"},"seed":{"type":"integer","description":"Random seed for reproducibility of the image generation"}},"required":["prompt"]},"output":{"type":"string","contentType":"image/png","format":"binary","description":"The generated image in PNG format"}}} \ No newline at end of file +{ + "id": "19547f04-7a6a-4f87-bf2c-f5e32fb12dc5", + "source": 1, + "name": "@cf/runwayml/stable-diffusion-v1-5-img2img", + "description": "Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images. Img2img generate a new image from an input image with Stable Diffusion. ", + "task": { + "id": "3d6e1f35-341b-4915-a6c8-9a7142a9033a", + "name": "Text-to-Image", + "description": "Generates images from input text. These models can be used to generate and modify images based on text prompts." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/runwayml/stable-diffusion-v1-5" + }, + { + "property_id": "terms", + "value": "https://github.com/runwayml/stable-diffusion/blob/main/LICENSE" + } + ], + "schema": { + "input": { + "type": "object", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "description": "A text description of the image you want to generate" + }, + "negative_prompt": { + "type": "string", + "description": "Text describing elements to avoid in the generated image" + }, + "height": { + "type": "integer", + "minimum": 256, + "maximum": 2048, + "description": "The height of the generated image in pixels" + }, + "width": { + "type": "integer", + "minimum": 256, + "maximum": 2048, + "description": "The width of the generated image in pixels" + }, + "image": { + "type": "array", + "description": "For use with img2img tasks. An array of integers that represent the image data constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + }, + "image_b64": { + "type": "string", + "description": "For use with img2img tasks. A base64-encoded string of the input image" + }, + "mask": { + "type": "array", + "description": "An array representing An array of integers that represent mask image data for inpainting constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + }, + "num_steps": { + "type": "integer", + "default": 20, + "maximum": 20, + "description": "The number of diffusion steps; higher values can improve quality but take longer" + }, + "strength": { + "type": "number", + "default": 1, + "description": "A value between 0 and 1 indicating how strongly to apply the transformation during img2img tasks; lower values make the output closer to the input image" + }, + "guidance": { + "type": "number", + "default": 7.5, + "description": "Controls how closely the generated image should adhere to the prompt; higher values make the image more aligned with the prompt" + }, + "seed": { + "type": "integer", + "description": "Random seed for reproducibility of the image generation" + } + }, + "required": [ + "prompt" + ] + }, + "output": { + "type": "string", + "contentType": "image/png", + "format": "binary", + "description": "The generated image in PNG format" + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/stable-diffusion-v1-5-inpainting.json b/src/content/workers-ai-models/stable-diffusion-v1-5-inpainting.json index 6c171f89b2d18d9..2c462251a7c7d1d 100644 --- a/src/content/workers-ai-models/stable-diffusion-v1-5-inpainting.json +++ b/src/content/workers-ai-models/stable-diffusion-v1-5-inpainting.json @@ -1 +1,103 @@ -{"id":"a9abaef0-3031-47ad-8790-d311d8684c6c","source":1,"name":"@cf/runwayml/stable-diffusion-v1-5-inpainting","description":"Stable Diffusion Inpainting is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input, with the extra capability of inpainting the pictures by using a mask.","task":{"id":"3d6e1f35-341b-4915-a6c8-9a7142a9033a","name":"Text-to-Image","description":"Generates images from input text. These models can be used to generate and modify images based on text prompts."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/runwayml/stable-diffusion-inpainting"},{"property_id":"terms","value":"https://github.com/runwayml/stable-diffusion/blob/main/LICENSE"}],"schema":{"input":{"type":"object","properties":{"prompt":{"type":"string","minLength":1,"description":"A text description of the image you want to generate"},"negative_prompt":{"type":"string","description":"Text describing elements to avoid in the generated image"},"height":{"type":"integer","minimum":256,"maximum":2048,"description":"The height of the generated image in pixels"},"width":{"type":"integer","minimum":256,"maximum":2048,"description":"The width of the generated image in pixels"},"image":{"type":"array","description":"For use with img2img tasks. An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},"image_b64":{"type":"string","description":"For use with img2img tasks. A base64-encoded string of the input image"},"mask":{"type":"array","description":"An array representing An array of integers that represent mask image data for inpainting constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},"num_steps":{"type":"integer","default":20,"maximum":20,"description":"The number of diffusion steps; higher values can improve quality but take longer"},"strength":{"type":"number","default":1,"description":"A value between 0 and 1 indicating how strongly to apply the transformation during img2img tasks; lower values make the output closer to the input image"},"guidance":{"type":"number","default":7.5,"description":"Controls how closely the generated image should adhere to the prompt; higher values make the image more aligned with the prompt"},"seed":{"type":"integer","description":"Random seed for reproducibility of the image generation"}},"required":["prompt"]},"output":{"type":"string","contentType":"image/png","format":"binary","description":"The generated image in PNG format"}}} \ No newline at end of file +{ + "id": "a9abaef0-3031-47ad-8790-d311d8684c6c", + "source": 1, + "name": "@cf/runwayml/stable-diffusion-v1-5-inpainting", + "description": "Stable Diffusion Inpainting is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input, with the extra capability of inpainting the pictures by using a mask.", + "task": { + "id": "3d6e1f35-341b-4915-a6c8-9a7142a9033a", + "name": "Text-to-Image", + "description": "Generates images from input text. These models can be used to generate and modify images based on text prompts." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/runwayml/stable-diffusion-inpainting" + }, + { + "property_id": "terms", + "value": "https://github.com/runwayml/stable-diffusion/blob/main/LICENSE" + } + ], + "schema": { + "input": { + "type": "object", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "description": "A text description of the image you want to generate" + }, + "negative_prompt": { + "type": "string", + "description": "Text describing elements to avoid in the generated image" + }, + "height": { + "type": "integer", + "minimum": 256, + "maximum": 2048, + "description": "The height of the generated image in pixels" + }, + "width": { + "type": "integer", + "minimum": 256, + "maximum": 2048, + "description": "The width of the generated image in pixels" + }, + "image": { + "type": "array", + "description": "For use with img2img tasks. An array of integers that represent the image data constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + }, + "image_b64": { + "type": "string", + "description": "For use with img2img tasks. A base64-encoded string of the input image" + }, + "mask": { + "type": "array", + "description": "An array representing An array of integers that represent mask image data for inpainting constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + }, + "num_steps": { + "type": "integer", + "default": 20, + "maximum": 20, + "description": "The number of diffusion steps; higher values can improve quality but take longer" + }, + "strength": { + "type": "number", + "default": 1, + "description": "A value between 0 and 1 indicating how strongly to apply the transformation during img2img tasks; lower values make the output closer to the input image" + }, + "guidance": { + "type": "number", + "default": 7.5, + "description": "Controls how closely the generated image should adhere to the prompt; higher values make the image more aligned with the prompt" + }, + "seed": { + "type": "integer", + "description": "Random seed for reproducibility of the image generation" + } + }, + "required": [ + "prompt" + ] + }, + "output": { + "type": "string", + "contentType": "image/png", + "format": "binary", + "description": "The generated image in PNG format" + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/stable-diffusion-xl-base-1.0.json b/src/content/workers-ai-models/stable-diffusion-xl-base-1.0.json index 212c86340780ad1..3343810075dbdb0 100644 --- a/src/content/workers-ai-models/stable-diffusion-xl-base-1.0.json +++ b/src/content/workers-ai-models/stable-diffusion-xl-base-1.0.json @@ -1 +1,103 @@ -{"id":"6d52253a-b731-4a03-b203-cde2d4fae871","source":1,"name":"@cf/stabilityai/stable-diffusion-xl-base-1.0","description":"Diffusion-based text-to-image generative model by Stability AI. Generates and modify images based on text prompts.","task":{"id":"3d6e1f35-341b-4915-a6c8-9a7142a9033a","name":"Text-to-Image","description":"Generates images from input text. These models can be used to generate and modify images based on text prompts."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://stability.ai/stable-diffusion"},{"property_id":"terms","value":"https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md"}],"schema":{"input":{"type":"object","properties":{"prompt":{"type":"string","minLength":1,"description":"A text description of the image you want to generate"},"negative_prompt":{"type":"string","description":"Text describing elements to avoid in the generated image"},"height":{"type":"integer","minimum":256,"maximum":2048,"description":"The height of the generated image in pixels"},"width":{"type":"integer","minimum":256,"maximum":2048,"description":"The width of the generated image in pixels"},"image":{"type":"array","description":"For use with img2img tasks. An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},"image_b64":{"type":"string","description":"For use with img2img tasks. A base64-encoded string of the input image"},"mask":{"type":"array","description":"An array representing An array of integers that represent mask image data for inpainting constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},"num_steps":{"type":"integer","default":20,"maximum":20,"description":"The number of diffusion steps; higher values can improve quality but take longer"},"strength":{"type":"number","default":1,"description":"A value between 0 and 1 indicating how strongly to apply the transformation during img2img tasks; lower values make the output closer to the input image"},"guidance":{"type":"number","default":7.5,"description":"Controls how closely the generated image should adhere to the prompt; higher values make the image more aligned with the prompt"},"seed":{"type":"integer","description":"Random seed for reproducibility of the image generation"}},"required":["prompt"]},"output":{"type":"string","contentType":"image/png","format":"binary","description":"The generated image in PNG format"}}} \ No newline at end of file +{ + "id": "6d52253a-b731-4a03-b203-cde2d4fae871", + "source": 1, + "name": "@cf/stabilityai/stable-diffusion-xl-base-1.0", + "description": "Diffusion-based text-to-image generative model by Stability AI. Generates and modify images based on text prompts.", + "task": { + "id": "3d6e1f35-341b-4915-a6c8-9a7142a9033a", + "name": "Text-to-Image", + "description": "Generates images from input text. These models can be used to generate and modify images based on text prompts." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://stability.ai/stable-diffusion" + }, + { + "property_id": "terms", + "value": "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md" + } + ], + "schema": { + "input": { + "type": "object", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "description": "A text description of the image you want to generate" + }, + "negative_prompt": { + "type": "string", + "description": "Text describing elements to avoid in the generated image" + }, + "height": { + "type": "integer", + "minimum": 256, + "maximum": 2048, + "description": "The height of the generated image in pixels" + }, + "width": { + "type": "integer", + "minimum": 256, + "maximum": 2048, + "description": "The width of the generated image in pixels" + }, + "image": { + "type": "array", + "description": "For use with img2img tasks. An array of integers that represent the image data constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + }, + "image_b64": { + "type": "string", + "description": "For use with img2img tasks. A base64-encoded string of the input image" + }, + "mask": { + "type": "array", + "description": "An array representing An array of integers that represent mask image data for inpainting constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + }, + "num_steps": { + "type": "integer", + "default": 20, + "maximum": 20, + "description": "The number of diffusion steps; higher values can improve quality but take longer" + }, + "strength": { + "type": "number", + "default": 1, + "description": "A value between 0 and 1 indicating how strongly to apply the transformation during img2img tasks; lower values make the output closer to the input image" + }, + "guidance": { + "type": "number", + "default": 7.5, + "description": "Controls how closely the generated image should adhere to the prompt; higher values make the image more aligned with the prompt" + }, + "seed": { + "type": "integer", + "description": "Random seed for reproducibility of the image generation" + } + }, + "required": [ + "prompt" + ] + }, + "output": { + "type": "string", + "contentType": "image/png", + "format": "binary", + "description": "The generated image in PNG format" + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/stable-diffusion-xl-lightning.json b/src/content/workers-ai-models/stable-diffusion-xl-lightning.json index 061cd9ee23dd1b2..7ccba1503a51397 100644 --- a/src/content/workers-ai-models/stable-diffusion-xl-lightning.json +++ b/src/content/workers-ai-models/stable-diffusion-xl-lightning.json @@ -1 +1,99 @@ -{"id":"7f797b20-3eb0-44fd-b571-6cbbaa3c423b","source":1,"name":"@cf/bytedance/stable-diffusion-xl-lightning","description":"SDXL-Lightning is a lightning-fast text-to-image generation model. It can generate high-quality 1024px images in a few steps.","task":{"id":"3d6e1f35-341b-4915-a6c8-9a7142a9033a","name":"Text-to-Image","description":"Generates images from input text. These models can be used to generate and modify images based on text prompts."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/ByteDance/SDXL-Lightning"}],"schema":{"input":{"type":"object","properties":{"prompt":{"type":"string","minLength":1,"description":"A text description of the image you want to generate"},"negative_prompt":{"type":"string","description":"Text describing elements to avoid in the generated image"},"height":{"type":"integer","minimum":256,"maximum":2048,"description":"The height of the generated image in pixels"},"width":{"type":"integer","minimum":256,"maximum":2048,"description":"The width of the generated image in pixels"},"image":{"type":"array","description":"For use with img2img tasks. An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},"image_b64":{"type":"string","description":"For use with img2img tasks. A base64-encoded string of the input image"},"mask":{"type":"array","description":"An array representing An array of integers that represent mask image data for inpainting constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},"num_steps":{"type":"integer","default":20,"maximum":20,"description":"The number of diffusion steps; higher values can improve quality but take longer"},"strength":{"type":"number","default":1,"description":"A value between 0 and 1 indicating how strongly to apply the transformation during img2img tasks; lower values make the output closer to the input image"},"guidance":{"type":"number","default":7.5,"description":"Controls how closely the generated image should adhere to the prompt; higher values make the image more aligned with the prompt"},"seed":{"type":"integer","description":"Random seed for reproducibility of the image generation"}},"required":["prompt"]},"output":{"type":"string","contentType":"image/png","format":"binary","description":"The generated image in PNG format"}}} \ No newline at end of file +{ + "id": "7f797b20-3eb0-44fd-b571-6cbbaa3c423b", + "source": 1, + "name": "@cf/bytedance/stable-diffusion-xl-lightning", + "description": "SDXL-Lightning is a lightning-fast text-to-image generation model. It can generate high-quality 1024px images in a few steps.", + "task": { + "id": "3d6e1f35-341b-4915-a6c8-9a7142a9033a", + "name": "Text-to-Image", + "description": "Generates images from input text. These models can be used to generate and modify images based on text prompts." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/ByteDance/SDXL-Lightning" + } + ], + "schema": { + "input": { + "type": "object", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "description": "A text description of the image you want to generate" + }, + "negative_prompt": { + "type": "string", + "description": "Text describing elements to avoid in the generated image" + }, + "height": { + "type": "integer", + "minimum": 256, + "maximum": 2048, + "description": "The height of the generated image in pixels" + }, + "width": { + "type": "integer", + "minimum": 256, + "maximum": 2048, + "description": "The width of the generated image in pixels" + }, + "image": { + "type": "array", + "description": "For use with img2img tasks. An array of integers that represent the image data constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + }, + "image_b64": { + "type": "string", + "description": "For use with img2img tasks. A base64-encoded string of the input image" + }, + "mask": { + "type": "array", + "description": "An array representing An array of integers that represent mask image data for inpainting constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + }, + "num_steps": { + "type": "integer", + "default": 20, + "maximum": 20, + "description": "The number of diffusion steps; higher values can improve quality but take longer" + }, + "strength": { + "type": "number", + "default": 1, + "description": "A value between 0 and 1 indicating how strongly to apply the transformation during img2img tasks; lower values make the output closer to the input image" + }, + "guidance": { + "type": "number", + "default": 7.5, + "description": "Controls how closely the generated image should adhere to the prompt; higher values make the image more aligned with the prompt" + }, + "seed": { + "type": "integer", + "description": "Random seed for reproducibility of the image generation" + } + }, + "required": [ + "prompt" + ] + }, + "output": { + "type": "string", + "contentType": "image/png", + "format": "binary", + "description": "The generated image in PNG format" + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/starling-lm-7b-beta.json b/src/content/workers-ai-models/starling-lm-7b-beta.json index 67e52f7b768483e..79c3e51a86611c2 100644 --- a/src/content/workers-ai-models/starling-lm-7b-beta.json +++ b/src/content/workers-ai-models/starling-lm-7b-beta.json @@ -1 +1,395 @@ -{"id":"e5ca943b-720f-4e66-aa8f-40e3d2770933","source":2,"name":"@hf/nexusflow/starling-lm-7b-beta","description":"We introduce Starling-LM-7B-beta, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF). Starling-LM-7B-beta is trained from Openchat-3.5-0106 with our new reward model Nexusflow/Starling-RM-34B and policy optimization method Fine-Tuning Language Models from Human Preferences (PPO).","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/Nexusflow/Starling-LM-7B-beta"},{"property_id":"max_batch_prefill_tokens","value":"8192"},{"property_id":"max_input_length","value":"3072"},{"property_id":"max_total_tokens","value":"4096"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "e5ca943b-720f-4e66-aa8f-40e3d2770933", + "source": 2, + "name": "@hf/nexusflow/starling-lm-7b-beta", + "description": "We introduce Starling-LM-7B-beta, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF). Starling-LM-7B-beta is trained from Openchat-3.5-0106 with our new reward model Nexusflow/Starling-RM-34B and policy optimization method Fine-Tuning Language Models from Human Preferences (PPO).", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/Nexusflow/Starling-LM-7B-beta" + }, + { + "property_id": "max_batch_prefill_tokens", + "value": "8192" + }, + { + "property_id": "max_input_length", + "value": "3072" + }, + { + "property_id": "max_total_tokens", + "value": "4096" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/tinyllama-1.1b-chat-v1.0.json b/src/content/workers-ai-models/tinyllama-1.1b-chat-v1.0.json index 9d303a58d890307..f96b8a2094b39a4 100644 --- a/src/content/workers-ai-models/tinyllama-1.1b-chat-v1.0.json +++ b/src/content/workers-ai-models/tinyllama-1.1b-chat-v1.0.json @@ -1 +1,383 @@ -{"id":"bf6ddd21-6477-4681-bbbe-24c3d5423e78","source":1,"name":"@cf/tinyllama/tinyllama-1.1b-chat-v1.0","description":"The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. This is the chat model finetuned on top of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "bf6ddd21-6477-4681-bbbe-24c3d5423e78", + "source": 1, + "name": "@cf/tinyllama/tinyllama-1.1b-chat-v1.0", + "description": "The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. This is the chat model finetuned on top of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/uform-gen2-qwen-500m.json b/src/content/workers-ai-models/uform-gen2-qwen-500m.json index 97312ad9e7d1f3b..fa7f000601dcdee 100644 --- a/src/content/workers-ai-models/uform-gen2-qwen-500m.json +++ b/src/content/workers-ai-models/uform-gen2-qwen-500m.json @@ -1 +1,85 @@ -{"id":"3dca5889-db3e-4973-aa0c-3a4a6bd22d29","source":1,"name":"@cf/unum/uform-gen2-qwen-500m","description":"UForm-Gen is a small generative vision-language model primarily designed for Image Captioning and Visual Question Answering. The model was pre-trained on the internal image captioning dataset and fine-tuned on public instructions datasets: SVIT, LVIS, VQAs datasets.","task":{"id":"882a91d1-c331-4eec-bdad-834c919942a8","name":"Image-to-Text","description":"Image to text models output a text from a given image. Image captioning or optical character recognition can be considered as the most common applications of image to text."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://www.unum.cloud/"}],"schema":{"input":{"oneOf":[{"type":"string","format":"binary","description":"Binary string representing the image contents."},{"type":"object","properties":{"temperature":{"type":"number","description":"Controls the randomness of the output; higher values produce more random results."},"prompt":{"type":"string","description":"The input text prompt for the model to generate a response."},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"max_tokens":{"type":"integer","default":512,"description":"The maximum number of tokens to generate in the response."}},"required":["image"]}]},"output":{"type":"object","contentType":"application/json","properties":{"description":{"type":"string"}}}}} \ No newline at end of file +{ + "id": "3dca5889-db3e-4973-aa0c-3a4a6bd22d29", + "source": 1, + "name": "@cf/unum/uform-gen2-qwen-500m", + "description": "UForm-Gen is a small generative vision-language model primarily designed for Image Captioning and Visual Question Answering. The model was pre-trained on the internal image captioning dataset and fine-tuned on public instructions datasets: SVIT, LVIS, VQAs datasets.", + "task": { + "id": "882a91d1-c331-4eec-bdad-834c919942a8", + "name": "Image-to-Text", + "description": "Image to text models output a text from a given image. Image captioning or optical character recognition can be considered as the most common applications of image to text." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://www.unum.cloud/" + } + ], + "schema": { + "input": { + "oneOf": [ + { + "type": "string", + "format": "binary", + "description": "Binary string representing the image contents." + }, + { + "type": "object", + "properties": { + "temperature": { + "type": "number", + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "prompt": { + "type": "string", + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "image": { + "oneOf": [ + { + "type": "array", + "description": "An array of integers that represent the image data constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + }, + { + "type": "string", + "format": "binary", + "description": "Binary string representing the image contents." + } + ] + }, + "max_tokens": { + "type": "integer", + "default": 512, + "description": "The maximum number of tokens to generate in the response." + } + }, + "required": [ + "image" + ] + } + ] + }, + "output": { + "type": "object", + "contentType": "application/json", + "properties": { + "description": { + "type": "string" + } + } + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/una-cybertron-7b-v2-bf16.json b/src/content/workers-ai-models/una-cybertron-7b-v2-bf16.json index 1e63b55f598e1bb..ad3d3b409258883 100644 --- a/src/content/workers-ai-models/una-cybertron-7b-v2-bf16.json +++ b/src/content/workers-ai-models/una-cybertron-7b-v2-bf16.json @@ -1 +1,379 @@ -{"id":"b7fe7ad2-aeaf-47d2-8bfa-7a5ae22a2ab4","source":1,"name":"@cf/fblgit/una-cybertron-7b-v2-bf16","description":"Cybertron 7B v2 is a 7B MistralAI based model, best on it's series. It was trained with SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "b7fe7ad2-aeaf-47d2-8bfa-7a5ae22a2ab4", + "source": 1, + "name": "@cf/fblgit/una-cybertron-7b-v2-bf16", + "description": "Cybertron 7B v2 is a 7B MistralAI based model, best on it's series. It was trained with SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/whisper-tiny-en.json b/src/content/workers-ai-models/whisper-tiny-en.json index 42d78b3f0cd8d12..ea118dc275dc395 100644 --- a/src/content/workers-ai-models/whisper-tiny-en.json +++ b/src/content/workers-ai-models/whisper-tiny-en.json @@ -1 +1,78 @@ -{"id":"2169496d-9c0e-4e49-8399-c44ee66bff7d","source":1,"name":"@cf/openai/whisper-tiny-en","description":"Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalize to many datasets and domains without the need for fine-tuning. This is the English-only version of the Whisper Tiny model which was trained on the task of speech recognition.","task":{"id":"dfce1c48-2a81-462e-a7fd-de97ce985207","name":"Automatic Speech Recognition","description":"Automatic speech recognition (ASR) models convert a speech signal, typically an audio input, to text."},"tags":[],"properties":[{"property_id":"beta","value":"true"}],"schema":{"input":{"oneOf":[{"type":"string","format":"binary"},{"type":"object","properties":{"audio":{"type":"array","description":"An array of integers that represent the audio data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},"source_lang":{"type":"string","description":"The language of the recorded audio"},"target_lang":{"type":"string","description":"The language to translate the transcription into. Currently only English is supported."}},"required":["audio"]}]},"output":{"type":"object","contentType":"application/json","properties":{"text":{"type":"string","description":"The transcription"},"word_count":{"type":"number"},"words":{"type":"array","items":{"type":"object","properties":{"word":{"type":"string"},"start":{"type":"number","description":"The second this word begins in the recording"},"end":{"type":"number","description":"The ending second when the word completes"}}}},"vtt":{"type":"string"}},"required":["text"]}}} \ No newline at end of file +{ + "id": "2169496d-9c0e-4e49-8399-c44ee66bff7d", + "source": 1, + "name": "@cf/openai/whisper-tiny-en", + "description": "Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalize to many datasets and domains without the need for fine-tuning. This is the English-only version of the Whisper Tiny model which was trained on the task of speech recognition.", + "task": { + "id": "dfce1c48-2a81-462e-a7fd-de97ce985207", + "name": "Automatic Speech Recognition", + "description": "Automatic speech recognition (ASR) models convert a speech signal, typically an audio input, to text." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + } + ], + "schema": { + "input": { + "oneOf": [ + { + "type": "string", + "format": "binary" + }, + { + "type": "object", + "properties": { + "audio": { + "type": "array", + "description": "An array of integers that represent the audio data constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + } + }, + "required": ["audio"] + } + ] + }, + "output": { + "type": "object", + "contentType": "application/json", + "properties": { + "text": { + "type": "string", + "description": "The transcription" + }, + "word_count": { + "type": "number" + }, + "words": { + "type": "array", + "items": { + "type": "object", + "properties": { + "word": { + "type": "string" + }, + "start": { + "type": "number", + "description": "The second this word begins in the recording" + }, + "end": { + "type": "number", + "description": "The ending second when the word completes" + } + } + } + }, + "vtt": { + "type": "string" + } + }, + "required": ["text"] + } + } +} diff --git a/src/content/workers-ai-models/whisper.json b/src/content/workers-ai-models/whisper.json index e7d1195e80e77f4..f6137338689167b 100644 --- a/src/content/workers-ai-models/whisper.json +++ b/src/content/workers-ai-models/whisper.json @@ -1 +1,86 @@ -{"id":"c1c12ce4-c36a-4aa6-8da4-f63ba4b8984d","source":1,"name":"@cf/openai/whisper","description":"Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.","task":{"id":"dfce1c48-2a81-462e-a7fd-de97ce985207","name":"Automatic Speech Recognition","description":"Automatic speech recognition (ASR) models convert a speech signal, typically an audio input, to text."},"tags":[],"properties":[{"property_id":"beta","value":"false"},{"property_id":"info","value":"https://openai.com/research/whisper"}],"schema":{"input":{"oneOf":[{"type":"string","format":"binary"},{"type":"object","properties":{"audio":{"type":"array","description":"An array of integers that represent the audio data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},"source_lang":{"type":"string","description":"The language of the recorded audio"},"target_lang":{"type":"string","description":"The language to translate the transcription into. Currently only English is supported."}},"required":["audio"]}]},"output":{"type":"object","contentType":"application/json","properties":{"text":{"type":"string","description":"The transcription"},"word_count":{"type":"number"},"words":{"type":"array","items":{"type":"object","properties":{"word":{"type":"string"},"start":{"type":"number","description":"The second this word begins in the recording"},"end":{"type":"number","description":"The ending second when the word completes"}}}},"vtt":{"type":"string"}},"required":["text"]}}} \ No newline at end of file +{ + "id": "c1c12ce4-c36a-4aa6-8da4-f63ba4b8984d", + "source": 1, + "name": "@cf/openai/whisper", + "description": "Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.", + "task": { + "id": "dfce1c48-2a81-462e-a7fd-de97ce985207", + "name": "Automatic Speech Recognition", + "description": "Automatic speech recognition (ASR) models convert a speech signal, typically an audio input, to text." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "false" + }, + { + "property_id": "info", + "value": "https://openai.com/research/whisper" + } + ], + "schema": { + "input": { + "oneOf": [ + { + "type": "string", + "format": "binary" + }, + { + "type": "object", + "properties": { + "audio": { + "type": "array", + "description": "An array of integers that represent the audio data constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + } + }, + "required": [ + "audio" + ] + } + ] + }, + "output": { + "type": "object", + "contentType": "application/json", + "properties": { + "text": { + "type": "string", + "description": "The transcription" + }, + "word_count": { + "type": "number" + }, + "words": { + "type": "array", + "items": { + "type": "object", + "properties": { + "word": { + "type": "string" + }, + "start": { + "type": "number", + "description": "The second this word begins in the recording" + }, + "end": { + "type": "number", + "description": "The ending second when the word completes" + } + } + } + }, + "vtt": { + "type": "string" + } + }, + "required": [ + "text" + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/zephyr-7b-beta-awq.json b/src/content/workers-ai-models/zephyr-7b-beta-awq.json index 59f8652f4f9eded..520e8d02a625fae 100644 --- a/src/content/workers-ai-models/zephyr-7b-beta-awq.json +++ b/src/content/workers-ai-models/zephyr-7b-beta-awq.json @@ -1 +1,383 @@ -{"id":"3976bab8-3810-4ad8-8580-ab1e22de7823","source":2,"name":"@hf/thebloke/zephyr-7b-beta-awq","description":"Zephyr 7B Beta AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Zephyr model variant.","task":{"id":"c329a1f9-323d-4e91-b2aa-582dd4188d34","name":"Text Generation","description":"Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."},"tags":[],"properties":[{"property_id":"beta","value":"true"},{"property_id":"info","value":"https://huggingface.co/TheBloke/zephyr-7B-beta-AWQ"}],"schema":{"input":{"type":"object","oneOf":[{"title":"Prompt","properties":{"prompt":{"type":"string","minLength":1,"maxLength":131072,"description":"The input text prompt for the model to generate a response."},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"raw":{"type":"boolean","default":false,"description":"If true, a chat template is not applied and you must adhere to the specific model's expected formatting."},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally using SSE, Server Sent Events."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."},"lora":{"type":"string","description":"Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."}},"required":["prompt"]},{"title":"Messages","properties":{"messages":{"type":"array","description":"An array of message objects representing the conversation history.","items":{"type":"object","properties":{"role":{"type":"string","description":"The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."},"content":{"type":"string","maxLength":131072,"description":"The content of the message as a string."}},"required":["role","content"]}},"image":{"oneOf":[{"type":"array","description":"An array of integers that represent the image data constrained to 8-bit unsigned integer values","items":{"type":"number","description":"A value between 0 and 255"}},{"type":"string","format":"binary","description":"Binary string representing the image contents."}]},"functions":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"code":{"type":"string"}},"required":["name","code"]}},"tools":{"type":"array","description":"A list of tools available for the assistant to use.","items":{"type":"object","oneOf":[{"properties":{"name":{"type":"string","description":"The name of the tool. More descriptive the better."},"description":{"type":"string","description":"A brief description of what the tool does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the tool.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]},{"properties":{"type":{"type":"string","description":"Specifies the type of tool (e.g., 'function')."},"function":{"type":"object","description":"Details of the function tool.","properties":{"name":{"type":"string","description":"The name of the function."},"description":{"type":"string","description":"A brief description of what the function does."},"parameters":{"type":"object","description":"Schema defining the parameters accepted by the function.","properties":{"type":{"type":"string","description":"The type of the parameters object (usually 'object')."},"required":{"type":"array","description":"List of required parameter names.","items":{"type":"string"}},"properties":{"type":"object","description":"Definitions of each parameter.","additionalProperties":{"type":"object","properties":{"type":{"type":"string","description":"The data type of the parameter."},"description":{"type":"string","description":"A description of the expected parameter."}},"required":["type","description"]}}},"required":["type","properties"]}},"required":["name","description","parameters"]}},"required":["type","function"]}]}},"stream":{"type":"boolean","default":false,"description":"If true, the response will be streamed back incrementally."},"max_tokens":{"type":"integer","default":256,"description":"The maximum number of tokens to generate in the response."},"temperature":{"type":"number","default":0.6,"minimum":0,"maximum":5,"description":"Controls the randomness of the output; higher values produce more random results."},"top_p":{"type":"number","minimum":0,"maximum":2,"description":"Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."},"top_k":{"type":"integer","minimum":1,"maximum":50,"description":"Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."},"seed":{"type":"integer","minimum":1,"maximum":9999999999,"description":"Random seed for reproducibility of the generation."},"repetition_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Penalty for repeated tokens; higher values discourage repetition."},"frequency_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Decreases the likelihood of the model repeating the same lines verbatim."},"presence_penalty":{"type":"number","minimum":0,"maximum":2,"description":"Increases the likelihood of the model introducing new topics."}},"required":["messages"]}]},"output":{"oneOf":[{"type":"object","contentType":"application/json","properties":{"response":{"type":"string","description":"The generated text response from the model"},"tool_calls":{"type":"array","description":"An array of tool calls requests made during the response generation","items":{"type":"object","properties":{"arguments":{"type":"object","description":"The arguments passed to be passed to the tool call request"},"name":{"type":"string","description":"The name of the tool to be called"}}}}}},{"type":"string","contentType":"text/event-stream","format":"binary"}]}}} \ No newline at end of file +{ + "id": "3976bab8-3810-4ad8-8580-ab1e22de7823", + "source": 2, + "name": "@hf/thebloke/zephyr-7b-beta-awq", + "description": "Zephyr 7B Beta AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Zephyr model variant.", + "task": { + "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34", + "name": "Text Generation", + "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + }, + { + "property_id": "info", + "value": "https://huggingface.co/TheBloke/zephyr-7B-beta-AWQ" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "maxLength": 131072, + "description": "The input text prompt for the model to generate a response." + }, + "raw": { + "type": "boolean", + "default": false, + "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting." + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Messages", + "properties": { + "messages": { + "type": "array", + "description": "An array of message objects representing the conversation history.", + "items": { + "type": "object", + "properties": { + "role": { + "type": "string", + "description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')." + }, + "content": { + "type": "string", + "maxLength": 131072, + "description": "The content of the message as a string." + } + }, + "required": [ + "role", + "content" + ] + } + }, + "functions": { + "type": "array", + "items": { + "type": "object", + "properties": { + "name": { + "type": "string" + }, + "code": { + "type": "string" + } + }, + "required": [ + "name", + "code" + ] + } + }, + "tools": { + "type": "array", + "description": "A list of tools available for the assistant to use.", + "items": { + "type": "object", + "oneOf": [ + { + "properties": { + "name": { + "type": "string", + "description": "The name of the tool. More descriptive the better." + }, + "description": { + "type": "string", + "description": "A brief description of what the tool does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the tool.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + }, + { + "properties": { + "type": { + "type": "string", + "description": "Specifies the type of tool (e.g., 'function')." + }, + "function": { + "type": "object", + "description": "Details of the function tool.", + "properties": { + "name": { + "type": "string", + "description": "The name of the function." + }, + "description": { + "type": "string", + "description": "A brief description of what the function does." + }, + "parameters": { + "type": "object", + "description": "Schema defining the parameters accepted by the function.", + "properties": { + "type": { + "type": "string", + "description": "The type of the parameters object (usually 'object')." + }, + "required": { + "type": "array", + "description": "List of required parameter names.", + "items": { + "type": "string" + } + }, + "properties": { + "type": "object", + "description": "Definitions of each parameter.", + "additionalProperties": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "The data type of the parameter." + }, + "description": { + "type": "string", + "description": "A description of the expected parameter." + } + }, + "required": [ + "type", + "description" + ] + } + } + }, + "required": [ + "type", + "properties" + ] + } + }, + "required": [ + "name", + "description", + "parameters" + ] + } + }, + "required": [ + "type", + "function" + ] + } + ] + } + }, + "stream": { + "type": "boolean", + "default": false, + "description": "If true, the response will be streamed back incrementally." + }, + "max_tokens": { + "type": "integer", + "default": 256, + "description": "The maximum number of tokens to generate in the response." + }, + "temperature": { + "type": "number", + "default": 0.6, + "minimum": 0, + "maximum": 5, + "description": "Controls the randomness of the output; higher values produce more random results." + }, + "top_p": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses." + }, + "top_k": { + "type": "integer", + "minimum": 1, + "maximum": 50, + "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises." + }, + "seed": { + "type": "integer", + "minimum": 1, + "maximum": 9999999999, + "description": "Random seed for reproducibility of the generation." + }, + "repetition_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Penalty for repeated tokens; higher values discourage repetition." + }, + "frequency_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Decreases the likelihood of the model repeating the same lines verbatim." + }, + "presence_penalty": { + "type": "number", + "minimum": 0, + "maximum": 2, + "description": "Increases the likelihood of the model introducing new topics." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "tool_calls": { + "type": "array", + "description": "An array of tool calls requests made during the response generation", + "items": { + "type": "object", + "properties": { + "arguments": { + "type": "object", + "description": "The arguments passed to be passed to the tool call request" + }, + "name": { + "type": "string", + "description": "The name of the tool to be called" + } + } + } + } + } + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file From 3e30b03a68cae9a99495eed1ebd6c538bbdd3788 Mon Sep 17 00:00:00 2001 From: Harley Turan Date: Tue, 3 Dec 2024 10:45:14 +0000 Subject: [PATCH 2/2] Add more schemas --- .../workers-ai-models/flux-1-schnell.json | 1 + .../llama-3-8b-instruct-awq.json | 4 - .../llama-3-8b-instruct.json | 4 - .../llama-3.1-8b-instruct-awq.json | 4 - .../llama-3.1-8b-instruct-fp8.json | 4 - .../llama-3.1-8b-instruct.json | 4 - .../llama-3.2-11b-vision-instruct.json | 4 - .../llama-3.2-1b-instruct.json | 4 - .../llama-3.2-3b-instruct.json | 4 - .../workers-ai-models/whisper-tiny-en.json | 158 +++++++++--------- 10 files changed, 82 insertions(+), 109 deletions(-) diff --git a/src/content/workers-ai-models/flux-1-schnell.json b/src/content/workers-ai-models/flux-1-schnell.json index 60e76d2052a9164..eb0c95b6deb9457 100644 --- a/src/content/workers-ai-models/flux-1-schnell.json +++ b/src/content/workers-ai-models/flux-1-schnell.json @@ -22,6 +22,7 @@ "prompt": { "type": "string", "minLength": 1, + "maxLength": 2048, "description": "A text description of the image you want to generate." }, "steps": { diff --git a/src/content/workers-ai-models/llama-3-8b-instruct-awq.json b/src/content/workers-ai-models/llama-3-8b-instruct-awq.json index 3326e41995be884..eaa38306420889c 100644 --- a/src/content/workers-ai-models/llama-3-8b-instruct-awq.json +++ b/src/content/workers-ai-models/llama-3-8b-instruct-awq.json @@ -10,10 +10,6 @@ }, "tags": [], "properties": [ - { - "property_id": "beta", - "value": "true" - }, { "property_id": "info", "value": "https://llama.meta.com" diff --git a/src/content/workers-ai-models/llama-3-8b-instruct.json b/src/content/workers-ai-models/llama-3-8b-instruct.json index 3a6d40d0ab5b799..4fcebca77ef9137 100644 --- a/src/content/workers-ai-models/llama-3-8b-instruct.json +++ b/src/content/workers-ai-models/llama-3-8b-instruct.json @@ -10,10 +10,6 @@ }, "tags": [], "properties": [ - { - "property_id": "beta", - "value": "true" - }, { "property_id": "info", "value": "https://llama.meta.com" diff --git a/src/content/workers-ai-models/llama-3.1-8b-instruct-awq.json b/src/content/workers-ai-models/llama-3.1-8b-instruct-awq.json index 83907c5c5123125..c97e9958c22b6c6 100644 --- a/src/content/workers-ai-models/llama-3.1-8b-instruct-awq.json +++ b/src/content/workers-ai-models/llama-3.1-8b-instruct-awq.json @@ -10,10 +10,6 @@ }, "tags": [], "properties": [ - { - "property_id": "beta", - "value": "true" - }, { "property_id": "terms", "value": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE" diff --git a/src/content/workers-ai-models/llama-3.1-8b-instruct-fp8.json b/src/content/workers-ai-models/llama-3.1-8b-instruct-fp8.json index 0bdfbc95fb2ecb8..b1733be14f578f1 100644 --- a/src/content/workers-ai-models/llama-3.1-8b-instruct-fp8.json +++ b/src/content/workers-ai-models/llama-3.1-8b-instruct-fp8.json @@ -10,10 +10,6 @@ }, "tags": [], "properties": [ - { - "property_id": "beta", - "value": "true" - }, { "property_id": "terms", "value": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE" diff --git a/src/content/workers-ai-models/llama-3.1-8b-instruct.json b/src/content/workers-ai-models/llama-3.1-8b-instruct.json index ec4604d6761a9a0..b4b5fd7c9d428d2 100644 --- a/src/content/workers-ai-models/llama-3.1-8b-instruct.json +++ b/src/content/workers-ai-models/llama-3.1-8b-instruct.json @@ -10,10 +10,6 @@ }, "tags": [], "properties": [ - { - "property_id": "beta", - "value": "true" - }, { "property_id": "terms", "value": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE" diff --git a/src/content/workers-ai-models/llama-3.2-11b-vision-instruct.json b/src/content/workers-ai-models/llama-3.2-11b-vision-instruct.json index 274629694bea7b3..29e783c4d70218c 100644 --- a/src/content/workers-ai-models/llama-3.2-11b-vision-instruct.json +++ b/src/content/workers-ai-models/llama-3.2-11b-vision-instruct.json @@ -10,10 +10,6 @@ }, "tags": [], "properties": [ - { - "property_id": "beta", - "value": "true" - }, { "property_id": "terms", "value": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE" diff --git a/src/content/workers-ai-models/llama-3.2-1b-instruct.json b/src/content/workers-ai-models/llama-3.2-1b-instruct.json index 3ffc3faf072fd15..1d37740559ce4cd 100644 --- a/src/content/workers-ai-models/llama-3.2-1b-instruct.json +++ b/src/content/workers-ai-models/llama-3.2-1b-instruct.json @@ -10,10 +10,6 @@ }, "tags": [], "properties": [ - { - "property_id": "beta", - "value": "true" - }, { "property_id": "terms", "value": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE" diff --git a/src/content/workers-ai-models/llama-3.2-3b-instruct.json b/src/content/workers-ai-models/llama-3.2-3b-instruct.json index 0b10dbe0ff6cc6a..e5fc5b67d49b6bb 100644 --- a/src/content/workers-ai-models/llama-3.2-3b-instruct.json +++ b/src/content/workers-ai-models/llama-3.2-3b-instruct.json @@ -10,10 +10,6 @@ }, "tags": [], "properties": [ - { - "property_id": "beta", - "value": "true" - }, { "property_id": "terms", "value": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE" diff --git a/src/content/workers-ai-models/whisper-tiny-en.json b/src/content/workers-ai-models/whisper-tiny-en.json index ea118dc275dc395..ac9f0cb89dcad4e 100644 --- a/src/content/workers-ai-models/whisper-tiny-en.json +++ b/src/content/workers-ai-models/whisper-tiny-en.json @@ -1,78 +1,82 @@ { - "id": "2169496d-9c0e-4e49-8399-c44ee66bff7d", - "source": 1, - "name": "@cf/openai/whisper-tiny-en", - "description": "Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalize to many datasets and domains without the need for fine-tuning. This is the English-only version of the Whisper Tiny model which was trained on the task of speech recognition.", - "task": { - "id": "dfce1c48-2a81-462e-a7fd-de97ce985207", - "name": "Automatic Speech Recognition", - "description": "Automatic speech recognition (ASR) models convert a speech signal, typically an audio input, to text." - }, - "tags": [], - "properties": [ - { - "property_id": "beta", - "value": "true" - } - ], - "schema": { - "input": { - "oneOf": [ - { - "type": "string", - "format": "binary" - }, - { - "type": "object", - "properties": { - "audio": { - "type": "array", - "description": "An array of integers that represent the audio data constrained to 8-bit unsigned integer values", - "items": { - "type": "number", - "description": "A value between 0 and 255" - } - } - }, - "required": ["audio"] - } - ] - }, - "output": { - "type": "object", - "contentType": "application/json", - "properties": { - "text": { - "type": "string", - "description": "The transcription" - }, - "word_count": { - "type": "number" - }, - "words": { - "type": "array", - "items": { - "type": "object", - "properties": { - "word": { - "type": "string" - }, - "start": { - "type": "number", - "description": "The second this word begins in the recording" - }, - "end": { - "type": "number", - "description": "The ending second when the word completes" - } - } - } - }, - "vtt": { - "type": "string" - } - }, - "required": ["text"] - } - } -} + "id": "2169496d-9c0e-4e49-8399-c44ee66bff7d", + "source": 1, + "name": "@cf/openai/whisper-tiny-en", + "description": "Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalize to many datasets and domains without the need for fine-tuning. This is the English-only version of the Whisper Tiny model which was trained on the task of speech recognition.", + "task": { + "id": "dfce1c48-2a81-462e-a7fd-de97ce985207", + "name": "Automatic Speech Recognition", + "description": "Automatic speech recognition (ASR) models convert a speech signal, typically an audio input, to text." + }, + "tags": [], + "properties": [ + { + "property_id": "beta", + "value": "true" + } + ], + "schema": { + "input": { + "oneOf": [ + { + "type": "string", + "format": "binary" + }, + { + "type": "object", + "properties": { + "audio": { + "type": "array", + "description": "An array of integers that represent the audio data constrained to 8-bit unsigned integer values", + "items": { + "type": "number", + "description": "A value between 0 and 255" + } + } + }, + "required": [ + "audio" + ] + } + ] + }, + "output": { + "type": "object", + "contentType": "application/json", + "properties": { + "text": { + "type": "string", + "description": "The transcription" + }, + "word_count": { + "type": "number" + }, + "words": { + "type": "array", + "items": { + "type": "object", + "properties": { + "word": { + "type": "string" + }, + "start": { + "type": "number", + "description": "The second this word begins in the recording" + }, + "end": { + "type": "number", + "description": "The ending second when the word completes" + } + } + } + }, + "vtt": { + "type": "string" + } + }, + "required": [ + "text" + ] + } + } +} \ No newline at end of file