🤗 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.

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

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

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Inference code for Llama models

The simplest, fastest repository for training/finetuning medium-sized GPTs.

High-Resolution Image Synthesis with Latent Diffusion Models

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

2025年最新总结，阿里，腾讯，百度，美团，头条等技术面试题目，以及答案，专家出题人分析汇总。

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

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

The official Meta Llama 3 GitHub site

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Graph Neural Network Library for PyTorch

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Fast and memory-efficient exact attention

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

PyTorch implementations of Generative Adversarial Networks.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Machine Learning Engineering Open Book

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Ongoing research training transformer models at scale

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

An open source implementation of CLIP.

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

Generate 3D objects conditioned on text or images