Stars
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.
Turn any Kiwix ZIM archive (offline Wikipedia, Stack Exchange, DevDocs, etc.) into an instant knowledge source for LLMs with a tiny CLI + Python server exposing searchable chunks, metadata and cita…
A novel Group Relative Reward Model (GRRM) framework enhances machine translation quality and reasoning capabilities by improving intra-group ranking through comparative analysis rather than isolat…
🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.
Automatically crawl arXiv papers daily and summarize them using AI. Illustrating them using GitHub Pages.
Evaluate your speech-to-text system with similarity measures such as word error rate (WER)
A community-maintained Python framework for creating mathematical animations.
Tool for live presentations using manim
A minimal C++ JSON reader based on a pushdown automaton
Pretrain, finetune any LLMs from huggingface on your own data.
A Survey of Attributions for Large Language Models
Large Language Model Text Generation Inference
📰 Must-read papers and blogs on Speculative Decoding ⚡️
使深信服（Sangfor）开发的非自由的 VPN 软件 EasyConnect 和 aTrust 运行在 docker 或 podman 中，并作为网关和/或提供 socks5、http 代理服务
H5 Page Maker, H5 Editor, LowCode. Make H5 as easy as building blocks. | 让H5制作像搭积木一样简单, 轻松搭建H5页面, H5网站, PC端网站,LowCode平台.
[WIP]en: web design tool || mobile page builder/editor || mini webflow for mobile page. zh: 类似易企秀的H5制作、建站工具、可视化搭建系统.
为腾讯微信优化的H5动效模板，帮助你快速构建全屏滚动型H5页面。
A unified evaluation framework for large language models
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
SoftVC VITS Singing Voice Conversion
MLNLP社区用来帮助大家避免论文投稿小错误的整理仓库。 Paper Writing Tips