Lyken17

Fooocus

Focus on prompting and generating

OpenVoice

Instant voice cloning by MyShell.

LLaVA

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

llama2.c

Inference Llama 2 in one file of pure C

llamafile

Distribute and run LLMs with a single file.

faster-whisper

Faster Whisper transcription with CTranslate2

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

LLMsPracticalGuide

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Baichuan-7B

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

rectg

经过精心筛选，从 5000+ 个电报群组/频道/机器人中挑选出的优质推荐！如果您有更多值得推荐的电报群组/频道/机器人，欢迎在 issues 中留言或提交 pull requests。感谢您的关注！

gdown

Google Drive Public File Downloader when Curl/Wget Fails

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

InjectLib

基于Ruby编写的命令行注入版本

EasyLM

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

kernl

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

llama2.rs

A fast llama2 decoder in pure Rust.

DoctorGLM

基于ChatGLM-6B的中文问诊模型

lint-action

✨ GitHub Action for detecting and auto-fixing lint errors

deep-learning-pytorch-huggingface

landmark-attention

Landmark Attention: Random-Access Infinite Context Length for Transformers

depyf

depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.

docker-aria2

Docker Aria2的最佳实践

PyTorrent

Simple BitTorrent client made in Python - Use for learning

LightSeq

Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers

t2m

Torrent to magnet converter

fast_bpe_tokenizer

fast bpe tokenizer, simple to understand, easy to use

Mini_Reverse_Proxy

不到100行代码实现一个Python迷你内网穿透、反向正向代理小工具

DatasetFactory

To publish datasets made by myself