Announcing AutoNLP: A new automatic way to train and deploy NLP models.

The AI community building the future.

Build, train and deploy state of the art models powered by the reference open source in natural language processing.

More than 2,000 organizations are using Hugging Face

Allen Institute for AI

non-profit • 47 models

Facebook AI

company • 39 models

Microsoft

company • 46 models

Grammarly

company

Google AI

company • 115 models

Typeform

company • 6 models

Musixmatch

company • 2 models

asteroid-team

non-profit

Model Hub

Featured models

Browse the model hub to discover, experiment and contribute to new state of the art models.

Explore models

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.

See pricing

Fill Mask

distilbert-base-uncased

Computation time on cpu: cached.

happiness

0.036

survival

0.031

salvation

0.017

freedom

0.017

unity

0.015

        [
        

        {
        

        "sequence": "[CLS] the goal of life is happiness. [SEP]",
        

        "score": 0.03619175776839256,
        

        "token": 8404,
        

        "token_str": "happiness"
        

        },
        

        {
        

        "sequence": "[CLS] the goal of life is survival. [SEP]",
        

        "score": 0.030553575605154037,
        

        "token": 7691,
        

        "token_str": "survival"
        

        },
        

        {
        

        "sequence": "[CLS] the goal of life is salvation. [SEP]",
        

        "score": 0.016977138817310333,
        

        "token": 12611,
        

        "token_str": "salvation"
        

        },
        

        {
        

        "sequence": "[CLS] the goal of life is freedom. [SEP]",
        

        "score": 0.01669847033917904,
        

        "token": 4071,
        

        "token_str": "freedom"
        

        },
        

        {
        

        "sequence": "[CLS] the goal of life is unity. [SEP]",
        

        "score": 0.015267263166606426,
        

        "token": 8499,
        

        "token_str": "unity"
        

        }
        

        ]

Token for:

          
            $
          
          curl -X POST \
          

          -H "Authorization: Bearer
          
          " \
          

          -H "Content-Type: application/json" \
          

          -d '
          
            {"inputs":"The goal of life is [MASK]."}
          
          ' \
          

          https://api-inference.huggingface.co/models/distilbert-base-uncased

Token Classification

dbmdz/bert-finetuned-conll03

Computation time on cpu: cached.

My name is Clara PER and I live in Berkeley LOC , California LOC . I work at this cool company called Hugging Face ORG .

        [
        

        {
        

        "entity_group": "PER",
        

        "score": 0.9957742094993591,
        

        "word": "Clara",
        

        "start": 11,
        

        "end": 16
        

        },
        

        {
        

        "entity_group": "LOC",
        

        "score": 0.9966296553611755,
        

        "word": "Berkeley",
        

        "start": 31,
        

        "end": 39
        

        },
        

        {
        

        "entity_group": "LOC",
        

        "score": 0.9990796446800232,
        

        "word": "California",
        

        "start": 41,
        

        "end": 51
        

        }
        

        ]

Token for:

          
            $
          
          curl -X POST \
          

          -H "Authorization: Bearer
          
          " \
          

          -H "Content-Type: application/json" \
          

          -d '
          
            {"inputs":"My name is Clara and I live in Berkeley, California."}
          
          ' \
          

          https://api-inference.huggingface.co/models/dbmdz/bert-large-cased-finetuned-conll03-english

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

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.

🐸

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 🤗.

🦄

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.

🐎

Victor Sanh et AL. 2019

DistilBERT

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

Website

Company

Resources

Social