Stars
This is the official repo for the paper "General365: Benchmarking General Reasoning in LLMs under High Difficulty and Diversity".
This is the official repo for the paper "AMO-Bench: Large Language Models Still Struggle in High School Math Competitions".
Reinforcement Learning via Self-Distillation (SDPO)
The absolute trainer to light up AI agents.
A version of verl to support diverse tool use [TMLR 2026]
Train your Agent model via our easy and efficient framework
Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).
Scalable toolkit for efficient model reinforcement
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
ChatWiki 微信公众号的AI知识库工作流Agent平台，RAG大模型AI客服机器人，致力于成为垂直领域的coze、n8n。
A PyTorch native platform for training generative AI models
TrendPublish: 全自动 AI 内容生成与发布系统 | 微信公众号自动化 | 多源数据抓取 (Twitter/X、网站) | DeepseekAI、千问、讯飞模型 | 智能内容分析排序 | 定时发布 | 多模板支持 | Node.js | TypeScript | AI 技术趋势跟踪工具
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
Machine Learning Engineering Open Book
OpenMMLab Detection Toolbox and Benchmark
SGLang is a high-performance serving framework for large language models and multimodal models.
Fully open reproduction of DeepSeek-R1
Python3 package for Chinese/English OCR,use paddleocr-v5 onnx model(~20MB), with ultra-fast inference speed. 基于ppocr-v5-onnx模型推理，中英文OCR开源SOTA，推理速度超快。
A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.
An Open Large Reasoning Model for Real-World Solutions