From 30efc2760b6937d6589777504502eece356ff4ef Mon Sep 17 00:00:00 2001 From: Wauplin <11801849+Wauplin@users.noreply.github.com> Date: Tue, 22 Jul 2025 03:35:55 +0000 Subject: [PATCH] Update Inference Providers documentation (automated) --- .../providers/featherless-ai.md | 6 +- docs/inference-providers/providers/groq.md | 2 +- .../providers/hf-inference.md | 58 +++++++++++++------ docs/inference-providers/providers/nebius.md | 10 ++++ docs/inference-providers/providers/novita.md | 4 +- .../inference-providers/providers/together.md | 4 +- .../tasks/chat-completion.md | 9 +-- .../tasks/image-segmentation.md | 2 +- .../tasks/image-text-to-text.md | 2 +- .../tasks/text-generation.md | 3 +- .../tasks/text-to-image.md | 2 +- docs/inference-providers/tasks/translation.md | 2 +- .../tasks/zero-shot-classification.md | 6 +- scripts/inference-providers/package.json | 4 +- scripts/inference-providers/pnpm-lock.yaml | 30 +++++----- 15 files changed, 91 insertions(+), 53 deletions(-) diff --git a/docs/inference-providers/providers/featherless-ai.md b/docs/inference-providers/providers/featherless-ai.md index 5eb562045..1353a0cc1 100644 --- a/docs/inference-providers/providers/featherless-ai.md +++ b/docs/inference-providers/providers/featherless-ai.md @@ -52,7 +52,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion). @@ -62,7 +62,7 @@ Find out more about Chat Completion (VLM) [here](../tasks/chat-completion). @@ -72,6 +72,6 @@ Find out more about Text Generation [here](../tasks/text_generation). diff --git a/docs/inference-providers/providers/groq.md b/docs/inference-providers/providers/groq.md index 2d77a0c61..9eb478646 100644 --- a/docs/inference-providers/providers/groq.md +++ b/docs/inference-providers/providers/groq.md @@ -60,7 +60,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion). diff --git a/docs/inference-providers/providers/hf-inference.md b/docs/inference-providers/providers/hf-inference.md index 7ea25965d..e692445f8 100644 --- a/docs/inference-providers/providers/hf-inference.md +++ b/docs/inference-providers/providers/hf-inference.md @@ -42,12 +42,14 @@ All supported HF Inference models can be found [here](https://huggingface.co/mod HF Inference is the serverless Inference API powered by Hugging Face. This service used to be called "Inference API (serverless)" prior to Inference Providers. If you are interested in deploying models to a dedicated and autoscaling infrastructure managed by Hugging Face, check out [Inference Endpoints](https://huggingface.co/docs/inference-endpoints/index) instead. +As of July 2025, hf-inference focuses mostly on CPU inference (e.g. embedding, text-ranking, text-classification, or smaller LLMs that have historical importance like BERT or GPT-2). + ## Supported tasks ### Automatic Speech Recognition -Find out more about Automatic Speech Recognition [here](../tasks/automatic-speech-recognition). +Find out more about Automatic Speech Recognition [here](../tasks/automatic_speech_recognition). -### Chat Completion (VLM) +### Chat Completion (LLM) -Find out more about Chat Completion (VLM) [here](../tasks/chat-completion). +Find out more about Chat Completion (LLM) [here](../tasks/chat-completion). ### Feature Extraction -Find out more about Feature Extraction [here](../tasks/feature-extraction). +Find out more about Feature Extraction [here](../tasks/feature_extraction). ### Object Detection -Find out more about Object Detection [here](../tasks/object-detection). +Find out more about Object Detection [here](../tasks/object_detection). +### Text Generation + +Find out more about Text Generation [here](../tasks/text_generation). + + + + ### Text To Image -Find out more about Text To Image [here](../tasks/text-to-image). +Find out more about Text To Image [here](../tasks/text_to_image). ### Token Classification -Find out more about Token Classification [here](../tasks/token-classification). +Find out more about Token Classification [here](../tasks/token_classification). + + +### Zero Shot Classification + +Find out more about Zero Shot Classification [here](../tasks/zero_shot_classification). + + diff --git a/docs/inference-providers/providers/nebius.md b/docs/inference-providers/providers/nebius.md index ddc50921c..a23441bef 100644 --- a/docs/inference-providers/providers/nebius.md +++ b/docs/inference-providers/providers/nebius.md @@ -74,6 +74,16 @@ Find out more about Feature Extraction [here](../tasks/feature_extraction). /> +### Text Generation + +Find out more about Text Generation [here](../tasks/text_generation). + + + + ### Text To Image Find out more about Text To Image [here](../tasks/text_to_image). diff --git a/docs/inference-providers/providers/novita.md b/docs/inference-providers/providers/novita.md index 82a826c09..8ebb67a1f 100644 --- a/docs/inference-providers/providers/novita.md +++ b/docs/inference-providers/providers/novita.md @@ -52,7 +52,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion). @@ -62,7 +62,7 @@ Find out more about Chat Completion (VLM) [here](../tasks/chat-completion). diff --git a/docs/inference-providers/providers/together.md b/docs/inference-providers/providers/together.md index 07a9c9574..13dac88cb 100644 --- a/docs/inference-providers/providers/together.md +++ b/docs/inference-providers/providers/together.md @@ -50,7 +50,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion). @@ -70,7 +70,7 @@ Find out more about Text Generation [here](../tasks/text_generation). diff --git a/docs/inference-providers/tasks/chat-completion.md b/docs/inference-providers/tasks/chat-completion.md index 13bd80bd5..ed1e0b20e 100644 --- a/docs/inference-providers/tasks/chat-completion.md +++ b/docs/inference-providers/tasks/chat-completion.md @@ -25,6 +25,7 @@ This is a subtask of [`text-generation`](https://huggingface.co/docs/inference-p - [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B): Smaller variant of one of the most powerful models. - [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct): Very powerful text generation model trained to follow instructions. - [microsoft/phi-4](https://huggingface.co/microsoft/phi-4): Powerful text generation model by Microsoft. +- [simplescaling/s1.1-32B](https://huggingface.co/simplescaling/s1.1-32B): A very powerful model with reasoning capabilities. - [Qwen/Qwen2.5-7B-Instruct-1M](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M): Strong conversational model that supports very long instructions. - [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct): Text generation model used to write code. - [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1): Powerful reasoning based open large language model. @@ -63,7 +64,7 @@ The API supports: @@ -73,7 +74,7 @@ conversational /> @@ -108,7 +109,7 @@ conversational /> | **                 (#2)** | _object_ | | | **                        tool_calls*** | _object[]_ | | | **                                function*** | _object_ | | -| **                                        parameters*** | _unknown_ | | +| **                                        parameters** | _unknown_ | | | **                                        description** | _string_ | | | **                                        name*** | _string_ | | | **                                id*** | _string_ | | @@ -145,7 +146,7 @@ conversational /> | **tool_prompt** | _string_ | A prompt to be appended before the tools | | **tools** | _object[]_ | A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. | | **        function*** | _object_ | | -| **                parameters*** | _unknown_ | | +| **                parameters** | _unknown_ | | | **                description** | _string_ | | | **                name*** | _string_ | | | **        type*** | _string_ | | diff --git a/docs/inference-providers/tasks/image-segmentation.md b/docs/inference-providers/tasks/image-segmentation.md index 197800740..24f69d233 100644 --- a/docs/inference-providers/tasks/image-segmentation.md +++ b/docs/inference-providers/tasks/image-segmentation.md @@ -34,7 +34,7 @@ Explore all available models and find the one that suits you best [here](https:/ diff --git a/docs/inference-providers/tasks/image-text-to-text.md b/docs/inference-providers/tasks/image-text-to-text.md index 1af52a723..4d3ce1489 100644 --- a/docs/inference-providers/tasks/image-text-to-text.md +++ b/docs/inference-providers/tasks/image-text-to-text.md @@ -33,7 +33,7 @@ Explore all available models and find the one that suits you best [here](https:/ diff --git a/docs/inference-providers/tasks/text-generation.md b/docs/inference-providers/tasks/text-generation.md index 51ecfbcbb..ad4d736ed 100644 --- a/docs/inference-providers/tasks/text-generation.md +++ b/docs/inference-providers/tasks/text-generation.md @@ -30,6 +30,7 @@ For more details about the `text-generation` task, check out its [dedicated page - [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B): Smaller variant of one of the most powerful models. - [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct): Very powerful text generation model trained to follow instructions. - [microsoft/phi-4](https://huggingface.co/microsoft/phi-4): Powerful text generation model by Microsoft. +- [simplescaling/s1.1-32B](https://huggingface.co/simplescaling/s1.1-32B): A very powerful model with reasoning capabilities. - [Qwen/Qwen2.5-7B-Instruct-1M](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M): Strong conversational model that supports very long instructions. - [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct): Text generation model used to write code. - [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1): Powerful reasoning based open large language model. @@ -41,7 +42,7 @@ Explore all available models and find the one that suits you best [here](https:/ diff --git a/docs/inference-providers/tasks/text-to-image.md b/docs/inference-providers/tasks/text-to-image.md index aed8e3c14..09234c36c 100644 --- a/docs/inference-providers/tasks/text-to-image.md +++ b/docs/inference-providers/tasks/text-to-image.md @@ -36,7 +36,7 @@ Explore all available models and find the one that suits you best [here](https:/ diff --git a/docs/inference-providers/tasks/translation.md b/docs/inference-providers/tasks/translation.md index 86a7ac19e..5aa8b1c61 100644 --- a/docs/inference-providers/tasks/translation.md +++ b/docs/inference-providers/tasks/translation.md @@ -33,7 +33,7 @@ Explore all available models and find the one that suits you best [here](https:/ diff --git a/docs/inference-providers/tasks/zero-shot-classification.md b/docs/inference-providers/tasks/zero-shot-classification.md index d046ba432..1c57edfb9 100644 --- a/docs/inference-providers/tasks/zero-shot-classification.md +++ b/docs/inference-providers/tasks/zero-shot-classification.md @@ -24,13 +24,17 @@ For more details about the `zero-shot-classification` task, check out its [dedic ### Recommended models +- [facebook/bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli): Powerful zero-shot text classification model. Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=zero-shot-classification&sort=trending). ### Using the API -There are currently no snippet examples for the **zero-shot-classification** task, as no providers support it yet. + diff --git a/scripts/inference-providers/package.json b/scripts/inference-providers/package.json index 0298ebcef..4bdc7b6fe 100644 --- a/scripts/inference-providers/package.json +++ b/scripts/inference-providers/package.json @@ -14,8 +14,8 @@ "author": "", "license": "ISC", "dependencies": { - "@huggingface/inference": "^4.3.2", - "@huggingface/tasks": "^0.19.22", + "@huggingface/inference": "^4.5.3", + "@huggingface/tasks": "^0.19.28", "@types/node": "^22.5.0", "handlebars": "^4.7.8", "node": "^20.17.0", diff --git a/scripts/inference-providers/pnpm-lock.yaml b/scripts/inference-providers/pnpm-lock.yaml index 36efe78c1..f7120f5c1 100644 --- a/scripts/inference-providers/pnpm-lock.yaml +++ b/scripts/inference-providers/pnpm-lock.yaml @@ -9,11 +9,11 @@ importers: .: dependencies: '@huggingface/inference': - specifier: ^4.3.2 - version: 4.3.2 + specifier: ^4.5.3 + version: 4.5.3 '@huggingface/tasks': - specifier: ^0.19.22 - version: 0.19.22 + specifier: ^0.19.28 + version: 0.19.28 '@types/node': specifier: ^22.5.0 version: 22.5.0 @@ -189,16 +189,16 @@ packages: cpu: [x64] os: [win32] - '@huggingface/inference@4.3.2': - resolution: {integrity: sha512-c7MJJPDbhb0Xy3JHvO3LaRhCDnfAthdmV3UiLCYH440UkIkECGwaLHAsWg9G2gdUrmcfzybZvZ0lAQhwsiTKnA==} + '@huggingface/inference@4.5.3': + resolution: {integrity: sha512-SAWKT+e32jSfxwYkRaBQx1rlfgzkHCu0PXbCbOpY0Pvx6Si5wHia2BzZZdwgrpldaRbmFClxmNJy6lfCzQYfOw==} engines: {node: '>=18'} - '@huggingface/jinja@0.5.0': - resolution: {integrity: sha512-Ptc03/jGRiYRoi0bUYKZ14MkDslsBRT24oxmsvUlfYrvQMldrxCevhPnT+hfX8awKTT8/f/0ZBBWldoeAcMHdQ==} + '@huggingface/jinja@0.5.1': + resolution: {integrity: sha512-yUZLld4lrM9iFxHCwFQ7D1HW2MWMwSbeB7WzWqFYDWK+rEb+WldkLdAJxUPOmgICMHZLzZGVcVjFh3w/YGubng==} engines: {node: '>=18'} - '@huggingface/tasks@0.19.22': - resolution: {integrity: sha512-jtRXsJZTES01X4gJ5VOUnEm3ONyyfXUcWKObbWkr/SQmjaH/kxtWqc2zVWKaxL4QLoXqXJ+T+Pi5xupMStSudQ==} + '@huggingface/tasks@0.19.28': + resolution: {integrity: sha512-MWop8xmlrg0TVnODB5dyL+qGpxEDfMYmIdToYDV1nqgf85Kcutjr/yaBj2Ydumn7WUWhvM71O4zji6zZURVOvw==} '@jridgewell/resolve-uri@3.1.2': resolution: {integrity: sha512-bRISgCIjP20/tbWSPWMEi54QVPRZExkuD9lJL+UIxUKtwVJA8wW1Trb1jMs1RFXo1CBTNZ/5hpC9QvmKWdopKw==} @@ -415,14 +415,14 @@ snapshots: '@esbuild/win32-x64@0.23.1': optional: true - '@huggingface/inference@4.3.2': + '@huggingface/inference@4.5.3': dependencies: - '@huggingface/jinja': 0.5.0 - '@huggingface/tasks': 0.19.22 + '@huggingface/jinja': 0.5.1 + '@huggingface/tasks': 0.19.28 - '@huggingface/jinja@0.5.0': {} + '@huggingface/jinja@0.5.1': {} - '@huggingface/tasks@0.19.22': {} + '@huggingface/tasks@0.19.28': {} '@jridgewell/resolve-uri@3.1.2': {}