Train transformer language models with reinforcement learning.

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Tk-Instruct is a Transformer model that is tuned to solve many NLP tasks by following instructions.

Task-based datasets, preprocessing, and evaluation for sequence models.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

A framework for few-shot evaluation of autoregressive language models.

A modular RL library to fine-tune language models to human preferences

The full minitorch student suite.

Expanding natural instructions

Dataaset Release for Explanations for CommonsenseQA, ACL 2021 Paper

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

Official style files for papers submitted to venues of the Association for Computational Linguistics

Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpeed

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

A PyTorch Platform for Distributed RL

BabyAI platform. A testbed for training agents to understand and execute language commands.