diff --git a/docs/inference-providers/providers/cohere.md b/docs/inference-providers/providers/cohere.md index a57ed10aa..1e63c6baa 100644 --- a/docs/inference-providers/providers/cohere.md +++ b/docs/inference-providers/providers/cohere.md @@ -56,6 +56,6 @@ Find out more about Chat Completion (VLM) [here](../tasks/chat-completion). diff --git a/docs/inference-providers/providers/fal-ai.md b/docs/inference-providers/providers/fal-ai.md index 279dd74a5..e04f7ab3b 100644 --- a/docs/inference-providers/providers/fal-ai.md +++ b/docs/inference-providers/providers/fal-ai.md @@ -64,6 +64,6 @@ Find out more about Text To Video [here](../tasks/text_to_video). diff --git a/docs/inference-providers/providers/hf-inference.md b/docs/inference-providers/providers/hf-inference.md index 35732d5f3..d1cc6dc4b 100644 --- a/docs/inference-providers/providers/hf-inference.md +++ b/docs/inference-providers/providers/hf-inference.md @@ -39,13 +39,23 @@ If you are interested in deploying models to a dedicated and autoscaling infrast ## Supported tasks +### Audio Classification + +Find out more about Audio Classification [here](../tasks/audio_classification). + + + + ### Automatic Speech Recognition Find out more about Automatic Speech Recognition [here](../tasks/automatic_speech_recognition). @@ -65,7 +75,7 @@ Find out more about Chat Completion (VLM) [here](../tasks/chat-completion). @@ -75,7 +85,77 @@ Find out more about Feature Extraction [here](../tasks/feature_extraction). + + +### Fill Mask + +Find out more about Fill Mask [here](../tasks/fill_mask). + + + + +### Image Classification + +Find out more about Image Classification [here](../tasks/image_classification). + + + + +### Image Segmentation + +Find out more about Image Segmentation [here](../tasks/image_segmentation). + + + + +### Object Detection + +Find out more about Object Detection [here](../tasks/object_detection). + + + + +### Question Answering + +Find out more about Question Answering [here](../tasks/question_answering). + + + + +### Summarization + +Find out more about Summarization [here](../tasks/summarization). + + + + +### Table Question Answering + +Find out more about Table Question Answering [here](../tasks/table_question_answering). + + @@ -108,3 +188,33 @@ Find out more about Text To Image [here](../tasks/text_to_image). providersMapping={ {"hf-inference":{"modelId":"black-forest-labs/FLUX.1-dev","providerModelId":"black-forest-labs/FLUX.1-dev"} } } /> + +### Token Classification + +Find out more about Token Classification [here](../tasks/token_classification). + + + + +### Translation + +Find out more about Translation [here](../tasks/translation). + + + + +### 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 e3bfcf430..53db03a1b 100644 --- a/docs/inference-providers/providers/nebius.md +++ b/docs/inference-providers/providers/nebius.md @@ -44,7 +44,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion). diff --git a/docs/inference-providers/register-as-a-provider.md b/docs/inference-providers/register-as-a-provider.md index 968fc1929..32e2f20ec 100644 --- a/docs/inference-providers/register-as-a-provider.md +++ b/docs/inference-providers/register-as-a-provider.md @@ -473,7 +473,11 @@ Here's how to add your documentation page: - Submit the Documentation PR: * Add your new `{provider-name}.handlebars` file. * Update the [partners table](./index#partners) to include your company or product. - + * Update the `_toctree.yml` file in the `docs/inference-providers/` directory to include your new documentation page in the "Providers" section, maintaining alphabetical order. + * Update the `scripts/inference-providers/scripts/generate.ts` file to include your provider in the `PROVIDERS_HUB_ORGS` and `PROVIDERS_URLS` constants, maintaining alphabetical order. + * Run `pnpm install` (if you haven't already) and then `pnpm run generate` at the root of the `scripts/inference-providers` repository to generate the documentation. + * Commit all your changes, including the manually edited files (provider page, `_toctree.yml`, partners table) and the files generated by the script. + * When you open the PR, please ping @Wauplin, @SBrandeis, @julien-c, and @hanouticelina for a review. If you need any assistance with these steps, please reach out – we're here to help you! ## FAQ diff --git a/docs/inference-providers/tasks/audio-classification.md b/docs/inference-providers/tasks/audio-classification.md index fcc01910f..a066b7be7 100644 --- a/docs/inference-providers/tasks/audio-classification.md +++ b/docs/inference-providers/tasks/audio-classification.md @@ -29,13 +29,17 @@ For more details about the `audio-classification` task, check out its [dedicated ### Recommended models +- [ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition](https://huggingface.co/ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition): An emotion recognition model. Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=audio-classification&sort=trending). ### Using the API -There are currently no snippet examples for the **audio-classification** task, as no providers support it yet. + diff --git a/docs/inference-providers/tasks/automatic-speech-recognition.md b/docs/inference-providers/tasks/automatic-speech-recognition.md index 6de05b874..18c5acbf9 100644 --- a/docs/inference-providers/tasks/automatic-speech-recognition.md +++ b/docs/inference-providers/tasks/automatic-speech-recognition.md @@ -38,7 +38,7 @@ Explore all available models and find the one that suits you best [here](https:/ diff --git a/docs/inference-providers/tasks/chat-completion.md b/docs/inference-providers/tasks/chat-completion.md index 72bf1e195..ded878c14 100644 --- a/docs/inference-providers/tasks/chat-completion.md +++ b/docs/inference-providers/tasks/chat-completion.md @@ -24,6 +24,7 @@ This is a subtask of [`text-generation`](https://huggingface.co/docs/inference-p - [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it): A text-generation model trained to follow instructions. - [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. +- [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. @@ -59,7 +60,7 @@ The API supports: @@ -69,7 +70,7 @@ conversational /> @@ -120,6 +121,11 @@ conversational /> | **         (#2)** | _object_ | | | **                type*** | _enum_ | Possible values: regex. | | **                value*** | _string_ | | +| **         (#3)** | _object_ | | +| **                type*** | _enum_ | Possible values: json_schema. | +| **                value*** | _object_ | | +| **                        name** | _string_ | Optional name identifier for the schema | +| **                        schema*** | _unknown_ | The actual JSON schema definition | | **seed** | _integer_ | | | **stop** | _string[]_ | Up to 4 sequences where the API will stop generating further tokens. | | **stream** | _boolean_ | | diff --git a/docs/inference-providers/tasks/feature-extraction.md b/docs/inference-providers/tasks/feature-extraction.md index 5f40fc3b6..3d9e60fd0 100644 --- a/docs/inference-providers/tasks/feature-extraction.md +++ b/docs/inference-providers/tasks/feature-extraction.md @@ -29,6 +29,7 @@ For more details about the `feature-extraction` task, check out its [dedicated p ### Recommended models +- [thenlper/gte-large](https://huggingface.co/thenlper/gte-large): A powerful feature extraction model for natural language processing tasks. Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=feature-extraction&sort=trending). @@ -37,7 +38,7 @@ Explore all available models and find the one that suits you best [here](https:/ diff --git a/docs/inference-providers/tasks/fill-mask.md b/docs/inference-providers/tasks/fill-mask.md index 9252ac746..d527ce0df 100644 --- a/docs/inference-providers/tasks/fill-mask.md +++ b/docs/inference-providers/tasks/fill-mask.md @@ -24,13 +24,17 @@ For more details about the `fill-mask` task, check out its [dedicated page](http ### Recommended models +- [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base): A multilingual model trained on 100 languages. Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=fill-mask&sort=trending). ### Using the API -There are currently no snippet examples for the **fill-mask** task, as no providers support it yet. + diff --git a/docs/inference-providers/tasks/image-classification.md b/docs/inference-providers/tasks/image-classification.md index 416446956..6c3864f8d 100644 --- a/docs/inference-providers/tasks/image-classification.md +++ b/docs/inference-providers/tasks/image-classification.md @@ -24,13 +24,18 @@ For more details about the `image-classification` task, check out its [dedicated ### Recommended models +- [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224): A strong image classification model. +- [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224): A robust image classification model. Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=image-classification&sort=trending). ### Using the API -There are currently no snippet examples for the **image-classification** task, as no providers support it yet. + diff --git a/docs/inference-providers/tasks/image-segmentation.md b/docs/inference-providers/tasks/image-segmentation.md index 24136417b..1ceca0e68 100644 --- a/docs/inference-providers/tasks/image-segmentation.md +++ b/docs/inference-providers/tasks/image-segmentation.md @@ -24,13 +24,17 @@ For more details about the `image-segmentation` task, check out its [dedicated p ### Recommended models +- [facebook/mask2former-swin-large-coco-panoptic](https://huggingface.co/facebook/mask2former-swin-large-coco-panoptic): Panoptic segmentation model trained on the COCO (common objects) dataset. Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=image-segmentation&sort=trending). ### Using the API -There are currently no snippet examples for the **image-segmentation** task, as no providers support it yet. + diff --git a/docs/inference-providers/tasks/object-detection.md b/docs/inference-providers/tasks/object-detection.md index 299a41788..3c36c4081 100644 --- a/docs/inference-providers/tasks/object-detection.md +++ b/docs/inference-providers/tasks/object-detection.md @@ -24,13 +24,17 @@ For more details about the `object-detection` task, check out its [dedicated pag ### Recommended models +- [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50): Solid object detection model pre-trained on the COCO 2017 dataset. Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=object-detection&sort=trending). ### Using the API -There are currently no snippet examples for the **object-detection** task, as no providers support it yet. + diff --git a/docs/inference-providers/tasks/question-answering.md b/docs/inference-providers/tasks/question-answering.md index e93c6c6de..2f1330014 100644 --- a/docs/inference-providers/tasks/question-answering.md +++ b/docs/inference-providers/tasks/question-answering.md @@ -24,13 +24,19 @@ For more details about the `question-answering` task, check out its [dedicated p ### Recommended models +- [deepset/roberta-base-squad2](https://huggingface.co/deepset/roberta-base-squad2): A robust baseline model for most question answering domains. +- [distilbert/distilbert-base-cased-distilled-squad](https://huggingface.co/distilbert/distilbert-base-cased-distilled-squad): Small yet robust model that can answer questions. +- [google/tapas-base-finetuned-wtq](https://huggingface.co/google/tapas-base-finetuned-wtq): A special model that can answer questions from tables. Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=question-answering&sort=trending). ### Using the API -There are currently no snippet examples for the **question-answering** task, as no providers support it yet. + diff --git a/docs/inference-providers/tasks/summarization.md b/docs/inference-providers/tasks/summarization.md index 1896451a0..6e0ff5ead 100644 --- a/docs/inference-providers/tasks/summarization.md +++ b/docs/inference-providers/tasks/summarization.md @@ -24,13 +24,17 @@ For more details about the `summarization` task, check out its [dedicated page]( ### Recommended models +- [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn): A strong summarization model trained on English news articles. Excels at generating factual summaries. Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=summarization&sort=trending). ### Using the API -There are currently no snippet examples for the **summarization** task, as no providers support it yet. + diff --git a/docs/inference-providers/tasks/table-question-answering.md b/docs/inference-providers/tasks/table-question-answering.md index ee41843a4..397c69dd1 100644 --- a/docs/inference-providers/tasks/table-question-answering.md +++ b/docs/inference-providers/tasks/table-question-answering.md @@ -24,13 +24,18 @@ For more details about the `table-question-answering` task, check out its [dedic ### Recommended models +- [microsoft/tapex-base](https://huggingface.co/microsoft/tapex-base): A table question answering model that is capable of neural SQL execution, i.e., employ TAPEX to execute a SQL query on a given table. +- [google/tapas-base-finetuned-wtq](https://huggingface.co/google/tapas-base-finetuned-wtq): A robust table question answering model. Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=table-question-answering&sort=trending). ### Using the API -There are currently no snippet examples for the **table-question-answering** task, as no providers support it yet. + diff --git a/docs/inference-providers/tasks/text-classification.md b/docs/inference-providers/tasks/text-classification.md index 48934e758..4d9d27f7c 100644 --- a/docs/inference-providers/tasks/text-classification.md +++ b/docs/inference-providers/tasks/text-classification.md @@ -26,6 +26,7 @@ For more details about the `text-classification` task, check out its [dedicated - [distilbert/distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert/distilbert-base-uncased-finetuned-sst-2-english): A robust model trained for sentiment analysis. - [ProsusAI/finbert](https://huggingface.co/ProsusAI/finbert): A sentiment analysis model specialized in financial sentiment. +- [meta-llama/Prompt-Guard-86M](https://huggingface.co/meta-llama/Prompt-Guard-86M): A model that can classify text generation attacks. Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=text-classification&sort=trending). diff --git a/docs/inference-providers/tasks/text-generation.md b/docs/inference-providers/tasks/text-generation.md index cca9c7676..0b1298517 100644 --- a/docs/inference-providers/tasks/text-generation.md +++ b/docs/inference-providers/tasks/text-generation.md @@ -29,6 +29,7 @@ For more details about the `text-generation` task, check out its [dedicated page - [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it): A text-generation model trained to follow instructions. - [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. +- [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. @@ -70,6 +71,11 @@ Explore all available models and find the one that suits you best [here](https:/ | **                 (#2)** | _object_ | | | **                        type*** | _enum_ | Possible values: regex. | | **                        value*** | _string_ | | +| **                 (#3)** | _object_ | | +| **                        type*** | _enum_ | Possible values: json_schema. | +| **                        value*** | _object_ | | +| **                                name** | _string_ | Optional name identifier for the schema | +| **                                schema*** | _unknown_ | The actual JSON schema definition | | **        max_new_tokens** | _integer_ | Maximum number of tokens to generate. | | **        repetition_penalty** | _number_ | The parameter for repetition penalty. 1.0 means no penalty. See [this paper](https://arxiv.org/pdf/1909.05858.pdf) for more details. | | **        return_full_text** | _boolean_ | Whether to prepend the prompt to the generated text | diff --git a/docs/inference-providers/tasks/text-to-video.md b/docs/inference-providers/tasks/text-to-video.md index 27cf71b5e..18411dc97 100644 --- a/docs/inference-providers/tasks/text-to-video.md +++ b/docs/inference-providers/tasks/text-to-video.md @@ -35,7 +35,7 @@ Explore all available models and find the one that suits you best [here](https:/ diff --git a/docs/inference-providers/tasks/token-classification.md b/docs/inference-providers/tasks/token-classification.md index 67ff322c3..3636602eb 100644 --- a/docs/inference-providers/tasks/token-classification.md +++ b/docs/inference-providers/tasks/token-classification.md @@ -24,13 +24,19 @@ For more details about the `token-classification` task, check out its [dedicated ### Recommended models +- [dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER): A robust performance model to identify people, locations, organizations and names of miscellaneous entities. +- [FacebookAI/xlm-roberta-large-finetuned-conll03-english](https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll03-english): A strong model to identify people, locations, organizations and names in multiple languages. +- [blaze999/Medical-NER](https://huggingface.co/blaze999/Medical-NER): A token classification model specialized on medical entity recognition. Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=token-classification&sort=trending). ### Using the API -There are currently no snippet examples for the **token-classification** task, as no providers support it yet. + diff --git a/docs/inference-providers/tasks/translation.md b/docs/inference-providers/tasks/translation.md index 667120ced..86a7ac19e 100644 --- a/docs/inference-providers/tasks/translation.md +++ b/docs/inference-providers/tasks/translation.md @@ -24,13 +24,17 @@ For more details about the `translation` task, check out its [dedicated page](ht ### Recommended models +- [google-t5/t5-base](https://huggingface.co/google-t5/t5-base): A general-purpose Transformer that can be used to translate from English to German, French, or Romanian. Explore all available models and find the one that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=translation&sort=trending). ### Using the API -There are currently no snippet examples for the **translation** task, as no providers support it yet. + 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/scripts/generate.ts b/scripts/inference-providers/scripts/generate.ts index bf1de7a7d..08286c294 100644 --- a/scripts/inference-providers/scripts/generate.ts +++ b/scripts/inference-providers/scripts/generate.ts @@ -1,4 +1,3 @@ -import { INFERENCE_PROVIDERS } from "@huggingface/inference"; import { PipelineType } from "@huggingface/tasks"; import Handlebars from "handlebars"; import * as fs from "node:fs/promises"; @@ -60,6 +59,7 @@ const PROVIDERS_URLS: Record = { sambanova: "https://sambanova.ai/", together: "https://together.xyz/", }; +const INFERENCE_PROVIDERS = Object.keys(PROVIDERS_HUB_ORGS); async function authFetchJson(url: string) { const headers = url.includes("huggingface.co") ? HEADERS : {};