From ed95053c290e7cdb2aaca24a4722844473674476 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Victor=20Mu=C5=A1tar?= Date: Mon, 14 Oct 2024 20:16:58 +0200 Subject: [PATCH 1/8] Add playground to chat-completion doc --- docs/api-inference/tasks/chat-completion.md | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/docs/api-inference/tasks/chat-completion.md b/docs/api-inference/tasks/chat-completion.md index 367be55db..92e4ae9af 100644 --- a/docs/api-inference/tasks/chat-completion.md +++ b/docs/api-inference/tasks/chat-completion.md @@ -28,6 +28,18 @@ This is a subtask of [`text-generation`](./text_generation) designed to generate - [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407): Very strong open-source large language model. +### API Playground + +For Chat Completion models, we provide an interactive UI Playground for easier testing: + +- Quickly iterate on your prompts from the UI. +- Set and override system, assistant and user messages. +- Browse and select models currently available in the Inference API. +- Compare the output of two models side-by-side. +- Adjust prompt parameters from the UI. +- Easily switch between UI view and code snippets. + +Access the Inference UI Playground and start exploring: [https://huggingface.co/playground](https://huggingface.co/playground) ### Using the API From 55d21217eecf434accaf5a7338362041a4156d02 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Victor=20Mu=C5=A1tar?= Date: Mon, 14 Oct 2024 20:18:13 +0200 Subject: [PATCH 2/8] Update chat-completion.md --- docs/api-inference/tasks/chat-completion.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/api-inference/tasks/chat-completion.md b/docs/api-inference/tasks/chat-completion.md index 92e4ae9af..b3d56a413 100644 --- a/docs/api-inference/tasks/chat-completion.md +++ b/docs/api-inference/tasks/chat-completion.md @@ -36,7 +36,7 @@ For Chat Completion models, we provide an interactive UI Playground for easier t - Set and override system, assistant and user messages. - Browse and select models currently available in the Inference API. - Compare the output of two models side-by-side. -- Adjust prompt parameters from the UI. +- Adjust requests parameters from the UI. - Easily switch between UI view and code snippets. Access the Inference UI Playground and start exploring: [https://huggingface.co/playground](https://huggingface.co/playground) From 07a0df8abfacb9dcb4deba504976b11e7939912f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Victor=20Mu=C5=A1tar?= Date: Mon, 14 Oct 2024 20:22:06 +0200 Subject: [PATCH 3/8] Update index.md --- docs/api-inference/index.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/api-inference/index.md b/docs/api-inference/index.md index 689bdf63b..a56bf7a08 100644 --- a/docs/api-inference/index.md +++ b/docs/api-inference/index.md @@ -24,6 +24,7 @@ The Serverless Inference API offers a fast and free way to explore thousands of - 🚀 **Instant Prototyping:** Access powerful models without setup. - 🎯 **Diverse Use Cases:** One API for text, image, and beyond. - 🔧 **Developer-Friendly:** Simple requests, fast responses. +- 💬 **Get Started quickly**: With the [Inference Playground](https://huggingface.co/playground) for Chat Completion models. --- From 02aaba493a766b6874edd8435aa13515fd79a1a1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Victor=20Mu=C5=A1tar?= Date: Mon, 14 Oct 2024 20:23:24 +0200 Subject: [PATCH 4/8] Update chat-completion.md --- docs/api-inference/tasks/chat-completion.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/api-inference/tasks/chat-completion.md b/docs/api-inference/tasks/chat-completion.md index b3d56a413..e0841b08c 100644 --- a/docs/api-inference/tasks/chat-completion.md +++ b/docs/api-inference/tasks/chat-completion.md @@ -34,7 +34,7 @@ For Chat Completion models, we provide an interactive UI Playground for easier t - Quickly iterate on your prompts from the UI. - Set and override system, assistant and user messages. -- Browse and select models currently available in the Inference API. +- Browse and select models currently available on the Inference API. - Compare the output of two models side-by-side. - Adjust requests parameters from the UI. - Easily switch between UI view and code snippets. From 232c01c8afcff35104a7dcc40d54be3fc72f948a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Victor=20Mu=C5=A1tar?= Date: Thu, 17 Oct 2024 10:38:49 +0200 Subject: [PATCH 5/8] Update chat-completion.md --- docs/api-inference/tasks/chat-completion.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/api-inference/tasks/chat-completion.md b/docs/api-inference/tasks/chat-completion.md index e0841b08c..8475bbb48 100644 --- a/docs/api-inference/tasks/chat-completion.md +++ b/docs/api-inference/tasks/chat-completion.md @@ -39,6 +39,8 @@ For Chat Completion models, we provide an interactive UI Playground for easier t - Adjust requests parameters from the UI. - Easily switch between UI view and code snippets. + + Access the Inference UI Playground and start exploring: [https://huggingface.co/playground](https://huggingface.co/playground) ### Using the API From 33a8c32ce7a5a001cb49330f96c44ab56da7a7b7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Victor=20Mu=C5=A1tar?= Date: Thu, 17 Oct 2024 10:43:51 +0200 Subject: [PATCH 6/8] Update index.md --- docs/api-inference/index.md | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/docs/api-inference/index.md b/docs/api-inference/index.md index a56bf7a08..7a21937b6 100644 --- a/docs/api-inference/index.md +++ b/docs/api-inference/index.md @@ -24,7 +24,6 @@ The Serverless Inference API offers a fast and free way to explore thousands of - 🚀 **Instant Prototyping:** Access powerful models without setup. - 🎯 **Diverse Use Cases:** One API for text, image, and beyond. - 🔧 **Developer-Friendly:** Simple requests, fast responses. -- 💬 **Get Started quickly**: With the [Inference Playground](https://huggingface.co/playground) for Chat Completion models. --- @@ -47,8 +46,16 @@ The documentation is organized into two sections: --- +## Inference Playground + +If you want to get started quickly with Chat Completion models use the Inference Playground to quickly text and compare models against your prompts. + + + +--- + ## Looking for custom support from the Hugging Face team? - HuggingFace Expert Acceleration Program + HuggingFace Expert Acceleration Program
From 46d52798f1dc155d895d4e0ecd77996b7f3d2b31 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Victor=20Mu=C5=A1tar?= Date: Thu, 17 Oct 2024 10:45:51 +0200 Subject: [PATCH 7/8] Update chat-completion.md --- docs/api-inference/tasks/chat-completion.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/docs/api-inference/tasks/chat-completion.md b/docs/api-inference/tasks/chat-completion.md index 80544e2c1..636754a37 100644 --- a/docs/api-inference/tasks/chat-completion.md +++ b/docs/api-inference/tasks/chat-completion.md @@ -26,11 +26,12 @@ This is a subtask of [`text-generation`](https://huggingface.co/docs/api-inferen - [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct): Small yet powerful text generation model. - [HuggingFaceH4/starchat2-15b-v0.1](https://huggingface.co/HuggingFaceH4/starchat2-15b-v0.1): Strong coding assistant model. - [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407): Very strong open-source large language model. -- [meta-llama/Llama-3.2-11B-Vision-Instruct](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct): Powerful vision language model with great visual understanding and reasoning capabilities. -- [microsoft/Phi-3.5-vision-instruct](https://huggingface.co/microsoft/Phi-3.5-vision-instruct): Strong image-text-to-text model. #### Conversational Vision-Language Models (VLMs) +- [meta-llama/Llama-3.2-11B-Vision-Instruct](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct): Powerful vision language model with great visual understanding and reasoning capabilities. +- [microsoft/Phi-3.5-vision-instruct](https://huggingface.co/microsoft/Phi-3.5-vision-instruct): Strong image-text-to-text model. + ### API Playground For Chat Completion models, we provide an interactive UI Playground for easier testing: From 68d0e0c13f0986f5046aae2aae4244bd64948c15 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Victor=20Mu=C5=A1tar?= Date: Thu, 17 Oct 2024 10:51:19 +0200 Subject: [PATCH 8/8] Update index.md --- docs/api-inference/index.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/api-inference/index.md b/docs/api-inference/index.md index 7a21937b6..24355440d 100644 --- a/docs/api-inference/index.md +++ b/docs/api-inference/index.md @@ -48,7 +48,7 @@ The documentation is organized into two sections: ## Inference Playground -If you want to get started quickly with Chat Completion models use the Inference Playground to quickly text and compare models against your prompts. +If you want to get started quickly with [Chat Completion models](https://huggingface.co/models?inference=warm&other=conversational&sort=trending) use the Inference Playground to quickly text and compare models against your prompts.