Stars
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agent RL)
Awesome RL Reasoning Recipes ("Triple R")
A streamlined and customizable framework for efficient large model evaluation and performance benchmarking
This is the first paper to explore how to effectively use RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incentivize reasoning ca…
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Integrate the DeepSeek API into popular softwares
verl: Volcano Engine Reinforcement Learning for LLMs
[ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification".
将微信读书划线和笔记同步到Readwise
🔥中文 prompt 精选🔥，ChatGPT 使用指南，提升 ChatGPT 可玩性和可用性！🚀
Streamlit — A faster way to build and share data apps.
A curated list of resources for using LLMs to develop more competitive grant applications.
A high-throughput and memory-efficient inference and serving engine for LLMs
Retrieval and Retrieval-augmented LLMs
A cross-platform framework using Vue.js
中文情感分析库(Chinese Sentiment))可对文本进行情绪分析、正负情感分析。Text analysis, supporting multiple methods including word count, readability, document similarity, sentiment analysis, Word2Vec .
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time
A generative speech model for daily dialogue.
Datawhale成员整理的面经，内容包括机器学习，CV，NLP，推荐，开发等，欢迎大家star
Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch
V2rayU,基于v2ray核心的mac版客户端,用于科学上网,使用swift编写,支持trojan,vmess,shadowsocks,socks5等服务协议,支持订阅, 支持二维码,剪贴板导入,手动配置,二维码分享等