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

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Grok open release

TensorFlow code and pre-trained models for BERT

2023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。

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

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

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

PyTorch Tutorial for Deep Learning Researchers

OpenMMLab Detection Toolbox and Benchmark

Universal LLM Deployment Engine with ML Compilation

Machine learning, in numpy

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

Fast and memory-efficient exact attention

🚀 一键部署！真正的 AI 聊天机器人！支持ChatGPT、文心一言、讯飞星火、Bing、Bard、ChatGLM、POE，多账号，人设调教，虚拟女仆、图片渲染、语音发送 | 支持 QQ、Telegram、Discord、微信 等平台

Mamba SSM architecture

Open deep learning compiler stack for cpu, gpu and specialized accelerators

A paper list of object detection using deep learning.

Pytorch implementation of convolutional neural network visualization techniques

Chinese version of GPT2 training code, using BERT tokenizer.

Official Python client library for kubernetes

OpenMMLab Pose Estimation Toolbox and Benchmark.

The GitHub repository for the paper "Informer" accepted by AAAI 2021.

A simple, fully convolutional model for real-time instance segmentation.

OpenMMLab Text Detection, Recognition and Understanding Toolbox

Deformable Convolutional Networks

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

SOTA Re-identification Methods and Toolbox

RepVGG: Making VGG-style ConvNets Great Again