A comparison of deepseek grpo and qwen gspo on Qwen2.5-1.5B-Instruct fine tunning.
☆170Mar 28, 2026Updated 4 months ago
Alternatives and similar repositories for grpo_reproduce
Users that are interested in grpo_reproduce are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆41Nov 16, 2025Updated 8 months ago
- Pretrain、Posttrain、RAG、Agent等大模型相关的基础项目合集☆39Dec 7, 2025Updated 8 months ago
- ☆18Mar 15, 2026Updated 4 months ago
- Local-first interview recording review reports with a Codex skill and CLI.☆77May 16, 2026Updated 2 months ago
- ☆145Jan 18, 2026Updated 6 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- some notes for opensource llm technical reorts☆19Mar 6, 2026Updated 5 months ago
- Personal Project: MPP-Qwen14B & MPP-Qwen-Next(Multimodal Pipeline Parallel based on Qwen-LM). Support [video/image/multi-image] {sft/conv…☆685Mar 10, 2025Updated last year
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,701Nov 21, 2025Updated 8 months ago
- A travel agent based on Qwen2.5, fine-tuned by SFT + DPO/PPO/GRPO using traveling question-answer dataset, a mindmap can be output using …☆81Jul 6, 2026Updated last month
- 复现大模型相关算法及一些学习记录☆3,494Jul 2, 2026Updated last month
- 这是一个从零开始构建的强化学习人类反馈（RLHF）学习代码库，实现了 PPO、GRPO、GSPO 以及相关的策略优化算法，并提供了清晰、可复现的训练流程。由于文档是由latex文件转译过来，如果md文件渲染异常，请用VScode的md插件打开☆90Dec 19, 2025Updated 7 months ago
- 超简单使用监督微调SFT和强化学习RL去训练领域Agent☆34Oct 20, 2025Updated 9 months ago
- ☆55Nov 22, 2025Updated 8 months ago
- Qwen3 Fine-tuning: Medical R1 Style Chat☆333May 31, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 大学Latex答辩模版，当前包含川大、哈工大、中科大。☆11Jul 22, 2024Updated 2 years ago
- 一个面向鞋服零售行业的智能导购系统，为企业导购提供 AI 驱动的功能，包括： - 商品智能文案生成（支持流式输出 SSE） - 基于用户行为的意图分析（Intent Engine） - 智能促单话术生成（Hybrid Rule + LLM） - 商品知识增强检索（RAG）…☆15Mar 13, 2026Updated 4 months ago
- Codex skill for reconstructing diagram images into editable Draw.io files☆22Jul 21, 2026Updated 2 weeks ago
- This project extracts feature points based on the Mediapipe open-source model, uses LSTM, CNN, and Vision of Transformer network models f…☆17Oct 11, 2025Updated 9 months ago
- 2024百度商业AI技术创新大赛赛道一：基于大模型的广告检索全国一等奖获奖方案☆19Feb 23, 2025Updated last year
- stm32f103单片机+wifi模块+电子墨水屏系统☆11Apr 4, 2018Updated 8 years ago
- 基于YOLOv5的交通道路目标检测和数据分析软件☆19Feb 27, 2025Updated last year
- 🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!☆54,531Updated this week
- 简单易理解的代码，用于在qwen上使用grpo加强数学能 力☆58May 14, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL☆5,280Nov 13, 2025Updated 8 months ago
- Minimal reproduction of OneRec☆1,737May 14, 2026Updated 2 months ago
- 基于LangGraph开发的智能体项目，可借助大模型自动调用工具规划旅游行程，包括景点搜索、交通查询、饭店酒店查询等功能☆43Aug 27, 2024Updated last year
- 📚 从零开始构建大模型☆32,835Updated this week
- 集成Qwen与DeepSeek等先进大语言模型，支持纯LLM+分类层模式及LLM+LoRA+分类层模式，使用transformers模块化设计和训练便于根据需要调整或替换组件。☆21Sep 1, 2025Updated 11 months ago
- 基于轻量级 Qwen2.5-0.5B 和 SigLIP 的视觉语言多模态模型实现,包含训练和 SFT 代码。分享训练和 SFT 相关代码,记录一下探索和学习的过程。欢迎一起交流讨论~☆22Aug 31, 2025Updated 11 months ago
- 🚀 2026届大模型算法岗实习面经 | 包含 DeepSeek/Qwen 技术报告解析、手撕 PPO/RoPE/Transformer、RLHF 核心与八股文 | 持续更新中...☆630Mar 28, 2026Updated 4 months ago
- A Python package to make Stable Diffusion Image Generation ridiculously easy☆18Jul 1, 2024Updated 2 years ago
- ☆44Nov 22, 2025Updated 8 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆513Oct 16, 2025Updated 9 months ago
- ☆107Oct 22, 2025Updated 9 months ago
- ☆11Mar 19, 2022Updated 4 years ago
- ☆781Jul 26, 2026Updated 2 weeks ago
- A set of examples based on verl for end-to-end RL training recipes.☆321Updated this week
- ☆24Feb 27, 2026Updated 5 months ago
- 2025腾讯广告算法大赛相关代码——官方baseline☆39Nov 4, 2025Updated 9 months ago