🤗 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.

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

Source code for the X Recommendation Algorithm

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

Go implementation of the Ethereum protocol

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

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

深度学习经典、新论文逐段精读

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

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

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.

State-of-the-art 2D and 3D Face Analysis Project

Library for fast text representation and classification.

A code-completion engine for Vim

Solidity, the Smart Contract Programming Language

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.

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

PyTorch implementations of Generative Adversarial Networks.

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Python package built to ease deep learning on graph, on top of existing DL frameworks.

This project is deprecated. Check my new project ChatHub:

Open Machine Learning Compiler Framework

Official inference library for Mistral models

Fast and Accurate ML in 3 Lines of Code

Reinforcement learning resources curated

This repository provides state of the art (SoTA) results for all machine learning problems. We do our best to keep this repository up to date. If you do find a problem's SoTA result is out of date …

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Utilities intended for use with Llama models.