Popular repositories Loading

1. grpo-gspo-dapo_reproduce grpo-gspo-dapo_reproduce Public

   该仓库实现了grpo、gspo、dapo算法对比，包括数据处理、vllm rollout、答案解析、奖励函数、算法实现、训练、评估、badcase分析等（没有采用hugging face，verl框架）

   Python 1

2. all-in-rag all-in-rag Public

   Forked from datawhalechina/all-in-rag

   🔍大模型应用开发实战一：RAG技术全栈指南，在线阅读地址：https://datawhalechina.github.io/all-in-rag/

   Python

3. reinforcement-learning-an-introduction reinforcement-learning-an-introduction Public

   Forked from ShangtongZhang/reinforcement-learning-an-introduction

   Python Implementation of Reinforcement Learning: An Introduction

   Python

4. pvz_demo pvz_demo Public

   JavaScript

5. llm_base llm_base Public

   Forked from TeenLucifer/llm_base

   Pretrain、Posttrain、RAG、Agent等大模型相关的基础项目合集

   Python

6. desktop desktop Public

   Forked from ora-space/desktop

   Rust