🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Models and examples built with TensorFlow

scikit-learn: machine learning in Python

A high-throughput and memory-efficient inference and serving engine for LLMs

Inference code for Llama models

A collection of learning resources for curious software engineers

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Making large AI models cheaper, faster and more accessible

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

结巴中文分词

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

Minimal examples of data structures and algorithms in Python

Code for the paper "Language Models are Unsupervised Multitask Learners"

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Best Practices on Recommendation Systems

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Train transformer language models with reinforcement learning.

Python Implementation of Reinforcement Learning: An Introduction

100+ Chinese Word Vectors 上百种预训练中文词向量

An open-source tool-augmented conversational language model from Fudan University

A framework for few-shot evaluation of language models.

微信助手：1.每日定时给好友（女友）发送定制消息。2.机器人自动回复好友。3.群助手功能（例如：查询垃圾分类、天气、日历、电影实时票房、快递物流、PM2.5等）

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

A PyTorch implementation of the Transformer model in "Attention is All You Need".