Hugging Face Hub documentation
What's the Hugging Face Hub?
We are helping the community work together towards the goal of advancing Artificial Intelligence 🔥.
Not one company, even the Tech Titans, will be able to “solve AI” by itself – the only way we'll achieve this is by sharing knowledge and resources. On the Hugging Face Hub we are building the largest collection of models, datasets and metrics in order to democratize and advance AI for everyone 🚀. The Hugging Face Hub works as a central place where anyone can share and explore models and datasets.
What's a repository?
The Hugging Face Hub hosts Git-based repositories which are storage spaces that can contain all your files 💾.
These repositories have multiple advantages over other hosting solutions:
- versioning
- commit history and diffs
- branches
On top of that, Hugging Face Hub repositories have many other advantages:
- Repos provide useful metadata about their tasks, languages, metrics, etc.
- Anyone can play with the model directly in the browser!
- An API is provided to use the models in production settings.
- Over 10 frameworks such as 🤗 Transformers, Asteroid and ESPnet support using models from the Hugging Face Hub.
What's a widget?
Many repos have a widget that allows anyone to do inference directly on the browser!
Here are some examples:
- Named Entity Recognition using spaCy.
- Image Classification using 🤗 Transformers
- Text to Speech using ESPnet.
- Sentence Similarity using Sentence Transformers.
What's the Inference API?
The Inference API allows you to send HTTP requests to models in the Hugging Face Hub. The Inference API is 2x to 10x faster than the widgets! ⚡⚡
How can I explore the Hugging Face Hub?
How is a model's type of inference API and widget determined?
To determine which pipeline and widget to display (text-classification, token-classification, translation, etc.), we analyze information in the repo such as the metadata provided in the model card and configuration files. This information is mapped to a single pipeline_tag. We choose to expose only one widget per model for simplicity.
For most use cases, the model type is determined from the tags. For example, if there is tag: text-classification in the metadata, the inferred pipeline_tag will be text-classification.
For 🤗 Transformers however, the model type is determined automatically from config.json. The architecture can be used to determine the type: for example, AutoModelForTokenClassification corresponds to token-classification. If you're really interested in this, you can see pseudo-code in this gist.
You can always manually override your pipeline type with pipeline_tag: xxx in your model card metadata.
What are all the possible task/widget types?
You can find all the supported tasks here.
Here are some with links to examples:
text-classification, for instanceroberta-large-mnlitoken-classification, for instancedbmdz/bert-large-cased-finetuned-conll03-englishquestion-answering, for instancedistilbert-base-uncased-distilled-squadtranslation, for instancet5-basesummarization, for instancefacebook/bart-large-cnnconversational, for instancefacebook/blenderbot-400M-distilltext-generation, for instancegpt2fill-mask, for instancedistilroberta-basezero-shot-classification(implemented on top of a nlitext-classificationmodel), for instancefacebook/bart-large-mnlitable-question-answering, for instancegoogle/tapas-base-finetuned-wtqsentence-similarity, for instanceosanseviero/full-sentence-distillroberta2
How can I load/push from/to the Hub?
You have access to the repos as with any other Git-based repository! You can even upload very large files.
Here is a video to learn more about it from our course!
What's the origin of 🤗 name?
🤗