zhufengyun

SurrealGAN

joplin

Joplin - the secure note taking and to-do app with synchronisation capabilities for Windows, macOS, Linux, Android and iOS.

webdataset

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

open_clip

An open source implementation of CLIP.

AudioCLIP

Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)

Godot-MUD-Server-Game-Engine

Welcome to the Text-based Multi User Dungeon (MUD) in Godot GDScript! This project aims to revive the classic MUD gaming experience in a modern framework. Developed in Godot 4+ by g023, this MUD provides a nostalgic journey into the realm of interactive storytelling and adventure.

snac

Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate

AutoX

A UiAutomator on android, does not need root access(安卓平台上的JavaScript自动化工具)

TrinityCore

TrinityCore Open Source MMO Framework (master = 11.0.2.56196, 3.3.5 = 3.3.5a.12340, wotlk_classic = 3.4.3.54261, cata classic = 4.4.0.55262)

docker-elk

The Elastic stack (ELK) powered by Docker and Compose.

Retrieval-based-Voice-Conversion-WebUI

Easily train a good VC model with voice data <= 10 mins!

openvpn-install

Set up your own OpenVPN server on Debian, Ubuntu, Fedora, CentOS or Arch Linux.

jiant

jiant is an nlp toolkit

Llama-Chinese

Llama中文社区，Llama3在线体验和微调模型已开放，实时汇总最新Llama3学习资料，已将所有代码更新适配Llama3，构建最好的中文Llama大模型，完全开源可商用

text-generation-inference

Large Language Model Text Generation Inference

llama_inference

llama inference for tencentpretrain

RWKV-Runner

A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.

rwkv-cpp-accelerated

A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependencies

GPTQ-triton

GPTQ inference Triton kernel

transformer-deploy

Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Chinese-LLaMA-Alpaca

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

Langchain-Chatchat

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

ChatFiles

Document Chatbot — multiple files. Powered by GPT / Embedding.

llama_index

LlamaIndex is a data framework for your LLM applications

JittorLLMs

计图大模型推理库，具有高性能、配置要求低、中文支持好、可移植等特点

FastChat

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

lion-pytorch

🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

pytorch-lightning-template

An easy/swift-to-adapt PyTorch-Lighting template. 套壳模板，简单易用，稍改原来Pytorch代码，即可适配Lightning。You can translate your previous Pytorch code much easier using this template, and keep your freedom to edit all the functions as well. Big-project-friendly as well. No need to rewrite your config in hydra.

petals

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading