aohan237

asyncnsq

asyncio (PEP 3156) nsq (message queue) client.

async_cron

crontab for python,with asyncio

aplay

python actor model using asyncio

cache-client

cache client with async support for mysql, postgresql,mongodb .etc

alpaca-lora

Instruct-tune LLaMA on consumer hardware

Anima

第一个开源的基于QLoRA的33B中文大语言模型First QLoRA based open source 33B Chinese LLM

Chinese-Vicuna

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

CLIP

Contrastive Language-Image Pretraining

containers

ConvNeXt

Code release for ConvNeXt model

epub.js

Enhanced eBooks in the browser.

fairseq

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

FastChat

The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

hf-hub

Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package

llama

Inference code for LLaMA models

llm

Run inference for Large Language Models on CPU, with Rust 🦀🚀🦙

mujoco

Multi-Joint dynamics with Contact. A general purpose physics simulator.

nats.py

Python3 client for NATS

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Real-ESRGAN

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

regex

rust regex cjk capture group name support

SegFormer

Official PyTorch implementation of SegFormer

stylegan3

Official PyTorch implementation of StyleGAN3

text-generation-inference

Large Language Model Text Generation Inference

TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Ultra-Light-Fast-Generic-Face-Detector-1MB

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

watermark-removal

a machine learning image inpainting task that instinctively removes watermarks from image indistinguishable from the ground truth image

WeChat-MiniProgram-AR-TFJS

A WeChat MiniProgram Face AR using TensorFlow.js (TFJS) and a face landmarks detection.

wireguard-install

WireGuard VPN installer for Linux servers

YOLOX

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/