diff --git a/src/content/workers-ai-models/llama-3.3-70b-instruct-fp8-fast.json b/src/content/workers-ai-models/llama-3.3-70b-instruct-fp8-fast.json new file mode 100644 index 00000000000000..4d92073c346da0 --- /dev/null +++ b/src/content/workers-ai-models/llama-3.3-70b-instruct-fp8-fast.json @@ -0,0 +1,452 @@ +{ + "id": "7a143886-c9bb-4a1c-be95-377b1973bc3b", + "source": 1, + "name": "@cf/meta/llama-3.3-70b-instruct-fp8-fast", + "description": "Llama 3.3 70B quantized to fp8 precision, optimized to be faster.", + "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." + }, + "created_at": "2024-12-06 17:09:18.338", + "tags": [], + "properties": [ + { + "property_id": "context_window", + "value": "24000" + }, + { + "property_id": "price", + "value": [ + { + "unit": "per M input tokens", + "price": 0.29, + "currency": "USD" + }, + { + "unit": "per M output tokens", + "price": 2.25, + "currency": "USD" + } + ] + }, + { + "property_id": "terms", + "value": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/LICENSE" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "description": "The input text prompt for the model to generate a response." + }, + "lora": { + "type": "string", + "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." + }, + "response_format": { + "title": "JSON Mode", + "type": "object", + "properties": { + "type": { + "type": "string", + "enum": [ + "json_object", + "json_schema" + ] + }, + "json_schema": {} + } + }, + "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." + } + }, + "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", + "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" + ] + } + ] + } + }, + "response_format": { + "title": "JSON Mode", + "type": "object", + "properties": { + "type": { + "type": "string", + "enum": [ + "json_object", + "json_schema" + ] + }, + "json_schema": {} + } + }, + "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." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "usage": { + "type": "object", + "description": "Usage statistics for the inference request", + "properties": { + "prompt_tokens": { + "type": "number", + "description": "Total number of tokens in input", + "default": 0 + }, + "completion_tokens": { + "type": "number", + "description": "Total number of tokens in output", + "default": 0 + }, + "total_tokens": { + "type": "number", + "description": "Total number of input and output tokens", + "default": 0 + } + } + }, + "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" + } + } + } + } + }, + "required": [ + "response" + ] + }, + { + "type": "string", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/llama-4-scout-17b-16e-instruct.json b/src/content/workers-ai-models/llama-4-scout-17b-16e-instruct.json new file mode 100644 index 00000000000000..19e5a95987ad03 --- /dev/null +++ b/src/content/workers-ai-models/llama-4-scout-17b-16e-instruct.json @@ -0,0 +1,510 @@ +{ + "id": "06455e78-19f7-487b-93cd-c05a3dd07813", + "source": 1, + "name": "@cf/meta/llama-4-scout-17b-16e-instruct", + "description": "Meta's Llama 4 Scout is a 17 billion parameter model with 16 experts that is natively multimodal. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.", + "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." + }, + "created_at": "2025-04-05 20:25:56.137", + "tags": [], + "properties": [ + { + "property_id": "context_window", + "value": "131000" + }, + { + "property_id": "price", + "value": [ + { + "unit": "per M input tokens", + "price": 0, + "currency": "USD" + }, + { + "unit": "per M output tokens", + "price": 0, + "currency": "USD" + } + ] + }, + { + "property_id": "terms", + "value": "https://github.com/meta-llama/llama-models/blob/main/models/llama4/LICENSE" + } + ], + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Ai_Cf_Meta_Llama_4_Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "description": "The input text prompt for the model to generate a response." + }, + "guided_json": { + "type": "object", + "description": "JSON schema that should be fulfilled for the response." + }, + "response_format": { + "title": "JSON Mode", + "type": "object", + "properties": { + "type": { + "type": "string", + "enum": [ + "json_object", + "json_schema" + ] + }, + "json_schema": {} + } + }, + "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": 0.15, + "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." + } + }, + "required": [ + "prompt" + ] + }, + { + "title": "Ai_Cf_Meta_Llama_4_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')." + }, + "tool_call_id": { + "type": "string", + "description": "The tool call id. Must be supplied for tool calls for Mistral-3. If you don't know what to put here you can fall back to 000000001", + "pattern": "[a-zA-Z0-9]{9}" + }, + "content": { + "oneOf": [ + { + "type": "string", + "description": "The content of the message as a string." + }, + { + "type": "array", + "items": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "Type of the content provided" + }, + "text": { + "type": "string" + }, + "image_url": { + "type": "object", + "properties": { + "url": { + "type": "string", + "pattern": "^data:*", + "description": "image uri with data (e.g. data:image/jpeg;base64,/9j/...). HTTP URL will not be accepted" + } + } + } + } + } + }, + { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "Type of the content provided" + }, + "text": { + "type": "string" + }, + "image_url": { + "type": "object", + "properties": { + "url": { + "type": "string", + "pattern": "^data:*", + "description": "image uri with data (e.g. data:image/jpeg;base64,/9j/...). HTTP URL will not be accepted" + } + } + } + } + } + ] + } + } + } + }, + "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" + ] + } + ] + } + }, + "response_format": { + "title": "JSON Mode", + "type": "object", + "properties": { + "type": { + "type": "string", + "enum": [ + "json_object", + "json_schema" + ] + }, + "json_schema": {} + } + }, + "guided_json": { + "type": "object", + "description": "JSON schema that should be fufilled for the 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": 0.15, + "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." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "usage": { + "type": "object", + "description": "Usage statistics for the inference request", + "properties": { + "prompt_tokens": { + "type": "number", + "description": "Total number of tokens in input", + "default": 0 + }, + "completion_tokens": { + "type": "number", + "description": "Total number of tokens in output", + "default": 0 + }, + "total_tokens": { + "type": "number", + "description": "Total number of input and output tokens", + "default": 0 + } + } + }, + "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" + } + } + } + } + }, + "required": [ + "response" + ] + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } +} \ No newline at end of file diff --git a/src/content/workers-ai-models/qwen2.5-coder-32b-instruct.json b/src/content/workers-ai-models/qwen2.5-coder-32b-instruct.json index e60cb146e997c8..6f45c93117af09 100644 --- a/src/content/workers-ai-models/qwen2.5-coder-32b-instruct.json +++ b/src/content/workers-ai-models/qwen2.5-coder-32b-instruct.json @@ -35,418 +35,5 @@ "value": "true" } ], - "schema": { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "lora": { - "type": "string", - "description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model." - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "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." - } - }, - "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", - "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" - ] - } - ] - } - }, - "response_format": { - "title": "JSON Mode", - "type": "object", - "properties": { - "type": { - "type": "string", - "enum": [ - "json_object", - "json_schema" - ] - }, - "json_schema": {} - } - }, - "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." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "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" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "format": "binary" - } - ] - } - } + "schema": {} } \ No newline at end of file diff --git a/src/content/workers-ai-models/qwq-32b.json b/src/content/workers-ai-models/qwq-32b.json index 0eebbabb0f18f6..5360cfce7ed34a 100644 --- a/src/content/workers-ai-models/qwq-32b.json +++ b/src/content/workers-ai-models/qwq-32b.json @@ -35,449 +35,448 @@ "value": "true" } ], - "schema": - { - "input": { - "type": "object", - "oneOf": [ - { - "title": "Prompt", - "properties": { - "prompt": { - "type": "string", - "minLength": 1, - "description": "The input text prompt for the model to generate a response." - }, - "guided_json": { - "type": "object", - "description": "JSON schema that should be fulfilled for the 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": 0.15, - "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." - } - }, - "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')." - }, - "tool_call_id": { - "type": "string", - "description": "The tool call id. Must be supplied for tool calls for Mistral-3. If you don't know what to put here you can fall back to 000000001", - "pattern": "[a-zA-Z0-9]{9}" - }, - "content": { - "oneOf": [ - { - "type": "string", - "description": "The content of the message as a string." - }, - { - "type": "array", - "items": { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content provided" - }, - "text": { - "type": "string" - }, - "image_url": { - "type": "object", - "properties": { - "url": { - "type": "string", - "pattern": "^data:*", - "description": "image uri with data (e.g. data:image/jpeg;base64,/9j/...). HTTP URL will not be accepted" - } - } - } - } - } - }, - { - "type": "object", - "properties": { - "type": { - "type": "string", - "description": "Type of the content provided" - }, - "text": { - "type": "string" - }, - "image_url": { - "type": "object", - "properties": { - "url": { - "type": "string", - "pattern": "^data:*", - "description": "image uri with data (e.g. data:image/jpeg;base64,/9j/...). HTTP URL will not be accepted" - } - } - } - } - } - ] - } - } - } - }, - "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" - ] - } - ] - } - }, - "guided_json": { - "type": "object", - "description": "JSON schema that should be fufilled for the 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": 0.15, - "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." - } - }, - "required": [ - "messages" - ] - } - ] - }, - "output": { - "oneOf": [ - { - "type": "object", - "contentType": "application/json", - "properties": { - "response": { - "type": "string", - "description": "The generated text response from the model" - }, - "usage": { - "type": "object", - "description": "Usage statistics for the inference request", - "properties": { - "prompt_tokens": { - "type": "number", - "description": "Total number of tokens in input", - "default": 0 - }, - "completion_tokens": { - "type": "number", - "description": "Total number of tokens in output", - "default": 0 - }, - "total_tokens": { - "type": "number", - "description": "Total number of input and output tokens", - "default": 0 - } - } - }, - "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" - } - } - } - } - }, - "required": [ - "response" - ] - }, - { - "type": "string", - "contentType": "text/event-stream", - "format": "binary" - } - ] - } - } + "schema": { + "input": { + "type": "object", + "oneOf": [ + { + "title": "Prompt", + "properties": { + "prompt": { + "type": "string", + "minLength": 1, + "description": "The input text prompt for the model to generate a response." + }, + "guided_json": { + "type": "object", + "description": "JSON schema that should be fulfilled for the 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": 0.15, + "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." + } + }, + "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')." + }, + "tool_call_id": { + "type": "string", + "description": "The tool call id. Must be supplied for tool calls for Mistral-3. If you don't know what to put here you can fall back to 000000001", + "pattern": "[a-zA-Z0-9]{9}" + }, + "content": { + "oneOf": [ + { + "type": "string", + "description": "The content of the message as a string." + }, + { + "type": "array", + "items": { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "Type of the content provided" + }, + "text": { + "type": "string" + }, + "image_url": { + "type": "object", + "properties": { + "url": { + "type": "string", + "pattern": "^data:*", + "description": "image uri with data (e.g. data:image/jpeg;base64,/9j/...). HTTP URL will not be accepted" + } + } + } + } + } + }, + { + "type": "object", + "properties": { + "type": { + "type": "string", + "description": "Type of the content provided" + }, + "text": { + "type": "string" + }, + "image_url": { + "type": "object", + "properties": { + "url": { + "type": "string", + "pattern": "^data:*", + "description": "image uri with data (e.g. data:image/jpeg;base64,/9j/...). HTTP URL will not be accepted" + } + } + } + } + } + ] + } + } + } + }, + "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" + ] + } + ] + } + }, + "guided_json": { + "type": "object", + "description": "JSON schema that should be fufilled for the 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": 0.15, + "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." + } + }, + "required": [ + "messages" + ] + } + ] + }, + "output": { + "oneOf": [ + { + "type": "object", + "contentType": "application/json", + "properties": { + "response": { + "type": "string", + "description": "The generated text response from the model" + }, + "usage": { + "type": "object", + "description": "Usage statistics for the inference request", + "properties": { + "prompt_tokens": { + "type": "number", + "description": "Total number of tokens in input", + "default": 0 + }, + "completion_tokens": { + "type": "number", + "description": "Total number of tokens in output", + "default": 0 + }, + "total_tokens": { + "type": "number", + "description": "Total number of input and output tokens", + "default": 0 + } + } + }, + "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" + } + } + } + } + }, + "required": [ + "response" + ] + }, + { + "type": "string", + "contentType": "text/event-stream", + "format": "binary" + } + ] + } + } } \ No newline at end of file