Nugine

GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

uv

An extremely fast Python package and project manager, written in Rust.

pykan

Kolmogorov Arnold Networks

Mos

一个用于在 macOS 上平滑你的鼠标滚动效果或单独设置滚动方向的小工具, 让你的滚轮爽如触控板 | A lightweight tool used to smooth scrolling and set scroll direction independently for your mouse on macOS

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

leedl-tutorial

《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

pytorch-grad-cam

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

easy-rl

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

catboost

A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.

lm-evaluation-harness

A framework for few-shot evaluation of language models.

cook

🍲 好的，今天我们来做菜！OK, Let's Cook!

mergekit

Tools for merging pretrained large language models.

DiffSinger

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

torchtune

A Native-PyTorch Library for LLM Fine-tuning

mmpretrain

OpenMMLab Pre-training Toolbox and Benchmark

phxpaxos

The Paxos library implemented in C++ that has been used in the WeChat production environment.

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

DRL

Deep Reinforcement Learning

circle

The compiler is available for download. Get it!

omegaconf

Flexible Python configuration system. The last one you will ever need.

diffusiondb

A large-scale text-to-image prompt gallery dataset based on Stable Diffusion

DeepSeek-MoE

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

ubpf

Userspace eBPF VM

jiwer

Evaluate your speech-to-text system with similarity measures such as word error rate (WER)

lighteval

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.

MyGO

[Paper][Preprint 2024] MyGO: Discrete Modality Information as Fine-Grained Tokens for Multi-modal Knowledge Graph Completion

wiper

Disk analyser and cleanup tool

argparse_dataclass

Declarative CLIs with argparse and dataclasses

phoenix_cuhksz_knowledge