State-of-the-art natural language processing for Jax, PyTorch and TensorFlow.

The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools.

Fast state-of-the-Art tokenizers optimized for research and production.

Get notified when your training ends with only two additional lines of code.

A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision.

Train state-of-the-art natural language processing models and deploy them in a scalable environment automatically.

Prune a model while finetuning or training.

Client library to download and publish models and other files on the huggingface.co hub.

A benchmark for comparing Transformer-based models.

(from Hugging Face) - The official course series provided by 🤗 Hugging Face.

(by @nielsrogge) - Tutorials for applying multiple models on real-world datasets.

(from AI2) - An open-source NLP research library.

Enabling easy use of Graph Neural Networks for NLP.

Transformers with PyTorch Lightning interface.

Extension to the Transformers library, integrating adapters into state-of-the-art language models.

A low-code AI workflow automation tool and performs various NLP tasks in the workflow pipeline.

(from OBSS) - State-of-the-art NLP through transformer models in a modular design and consistent APIs.

A very simple framework for state-of-the-art NLP.

(from UKPLab) - Widely used encoders computing dense vector representations for sentences, paragraphs, and images.

(from Microsoft) - An easy unsupervised sentence embedding approach with whitening.

(from Princeton) - State-of-the-art sentence embedding with contrastive learning.

(from Princeton) - Learning dense representations of phrases at scale.

(from Tencent) - An inference engine for transformers with fast C++ API.

(from Nvidia) - A script and recipe to run the highly optimized transformer-based encoder and decoder component on…

(from ByteDance) - A high performance inference library for sequence processing and generation implemented in CUDA.

(from Microsoft) - Efficient implementation of popular sequence models (e.g., Bart, ProphetNet) for text generation,…

(from TUNiB) - A library for model parallel deployment.

(from TUNiB) - A library that supports various features to help you train large-scale models.

(from Microsoft) - Deepspeed-ZeRO - scales any model size with zero to no changes to the model. Integrated with HF…

(from Facebook) - Implements ZeRO protocol as well. Integrated with HF Trainer.

(from Hpcaitech) - A Unified Deep Learning System for Large-Scale Parallel Training (1D, 2D, 2.5D, 3D and sequence…

PyTorch-based modular, configuration-driven framework for knowledge distillation.

(from HFL) - State-of-the-art distillation methods to compress language models.

(from Microsoft) - Compressing BERT by progressively replacing the components of the original BERT.

(from UVa) - A Python framework for adversarial attacks, data augmentation, and model training in NLP.

(from Fudan) - A unified multilingual robustness evaluation toolkit for NLP.

(from THU) - An open-source textual adversarial attack toolkit.

A neural language style transfer framework to transfer text smoothly between styles.

A contrastive framework for self-supervised sentence representation transfer.

Implementation of different architectures for emotion recognition in conversations.

A framework for detecting, highlighting and correcting grammatical errors on natural language text.

A deep learning-based translation library based on HF Transformers.

(from UKPLab) - Easy-to-use, state-of-the-art translation library and Docker images based on HF Transformers.

(from Princeton) - Entity and relation extraction from text.

A self-supervised speech pre-training and representation learning toolkit.

A PyTorch-based speech toolkit.

(from Kakao) - A vision-and-language transformer Without convolution or region supervision.

Fine-tune transformers using Proximal Policy Optimization (PPO) to align with human preferences.

(from deepset) - End-to-end framework for developing and deploying question-answering systems in the wild.

(from Nvidia) - A flexible and efficient library powered by Transformers for sequential and session-based…

(from OBSS) - Easy to use tool for evaluating NLP model outputs, spesifically for NLG (Natural Language Generation),…

Interactively explore your HF dataset with one line of code. Use model results (e.g. embeddings, predictions) to…

Jina integration of Hugging Face Accelerated API.

(from Stanford) - A fast and accurate retrieval model, enabling scalable BERT-based search over large text collections…

Making it easier than ever to train Hugging Face Transformer models in Amazon SageMaker.

Collaboration on enabling Transformers in Snapdragon.

A benchmark for comparing Transformer-based models.