awesome-huggingface

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.

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

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

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

Prune a model while finetuning or training.

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

An open-source NLP research library.

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

Enabling easy use of Graph Neural Networks for NLP.

Transformers with PyTorch Lightning interface.

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

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

Compressing BERT by progressively replacing the components of the original BERT.

State-of-the-art distillation methods to compress language models.

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

A fast and accurate retrieval model, enabling scalable BERT-based search over large text collections in tens of milliseconds.

Jina integration of Hugging Face Accelerated API.

Weaviate integration of Hugging Face Transformers.

A Unified Deep Learning System for Large-Scale Parallel Training (1D, 2D, 2.5D, 3D and sequence parallelism, and ZeRO protocol).

Deepspeed-ZeRO - scales any model size with zero to no changes to the model.

Implements ZeRO protocol as well.

A library that supports various features to help you train large-scale models.

A library for model parallel deployment.

A contrastive framework for self-supervised sentence representation transfer.

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

Implementation of different architectures for emotion recognition in conversations.