The AI community building the future.

Build, train and deploy state of the art models powered by the reference open source in machine learning.

On demand

Inference API

Serve your models directly from Hugging Face infrastructure and run large scale NLP models in milliseconds with just a few lines of code.

Learn more
Fill-Mask
Mask token: [MASK]
Examples
Examples
This model can be loaded on the Inference API on-demand.
Token Classification
Examples
Examples
This model can be loaded on the Inference API on-demand.

Open Source

Transformers

Transformers is our natural language processing library and our hub is now open to all ML models, with support from libraries like Flair, Asteroid, ESPnet, Pyannote, and more to come.

Check documentation
huggingface@transformers:~
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
model = AutoModelForMaskedLM.from_pretrained("bert-base-uncased")
Science

Our Research contributions

We’re on a journey to advance and democratize NLP for everyone. Along the way, we contribute to the development of technology for the better.

📚

HMTL

Hierarchical Multi-Task Learning

Our paper has been accepted to AAAI 2019. We have open-sourced code and demo.

Read more

🐸

Thomas Wolf et AL.

Meta-learning for language modeling

Our workshop paper on Meta-Learning a Dynamical Language Model was accepted to ICLR 2018. We use our implementation to power 🤗.

Read more

🦄

Auto-complete your thoughts

Write with Transformers

This web app, built by the Hugging Face team, is the official demo of the Transformers repository's text generation capabilities.

Start writing

🤖

State of the art

Neuralcoref

Our coreference resolution module is now the top open source library for coreference. You can train it on your own dataset and language.

Read more

🐎

Victor Sanh et AL. 2019

DistilBERT

Distilllation. A smaller, faster, lighter, cheaper version of BERT. Code and weights are available through Transformers.

Read more