A comparison of deepseek grpo and qwen gspo on Qwen2.5-1.5B-Instruct fine tunning.
☆172Mar 28, 2026Updated 7 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:
- ☆175Mar 18, 2026Updated 7 months ago
- Fine-tune Qwen2.5-VL-7B on custom visual QA tasks using LoRA + Accelerate, supporting single/multi-GPU training on COCO 2014 dataset.☆30Apr 28, 2025Updated last year
- ☆156Jan 18, 2026Updated 9 months ago
- some notes for opensource llm technical reorts☆20Mar 6, 2026Updated 7 months ago
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,716Nov 21, 2025Updated 11 months ago
- 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.
- Develop based on "HKUDS/nanobot" from github, adding a few useful features for better utilization via feishu.☆70Jun 9, 2026Updated 4 months ago
- 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 10 months ago
- 复现大模型相关算法及一些学习记录☆3,561Jul 2, 2026Updated 3 months ago
- 科大讯飞多模态RAG图文问答挑战赛☆75Aug 4, 2025Updated last year
- WebResearcher: An Iterative Deep-Research Agent，迭代式深度研究智能体☆50Feb 13, 2026Updated 8 months ago
- ☆55Nov 22, 2025Updated 11 months ago
- Qwen3 Fine-tuning: Medical R1 Style Chat☆334May 31, 2025Updated last year
- 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
- Multi-Modal-AI-Orchestrator (Reset version),AI Full-modal Full-agent:Text → Image → Music → Lights → Video, Includes "Scenario Director,…☆102Nov 5, 2025Updated 11 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- 这是一个从头训练大语言模型的项目，包括预训练、微调和直接偏好优化，模型拥有1B参数，支持中英文。☆880Feb 18, 2025Updated last year
- 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）…☆17Mar 13, 2026Updated 7 months ago
- 🎙️ CosyVoice LoRA 微调框架：LLM+Flow 联合训练，实现无 Prompt 语音合成☆14Jan 5, 2026Updated 9 months ago
- Qwen2.5 0.5B GRPO☆87Feb 16, 2025Updated last year
- 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
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,910Apr 18, 2025Updated last year
- official implementation of "CLIP-VQDiffusion : Langauge Free Training of Text To Image generation using CLIP and vector quantized diffusi…☆19Sep 5, 2024Updated 2 years ago
- 将SmolVLM2的视觉头与Qwen3-0.6B模型进行了拼接微调☆613Sep 8, 2025Updated last year
- A curated collection of papers and projects on analyzing, extracting, and reproducing chain-of-thought reasoning from black-box models.☆50Aug 19, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆20Aug 22, 2025Updated last year
- ☆22Dec 18, 2025Updated 10 months ago
- ☆901Jul 26, 2026Updated 3 months ago
- 简单易理解的代码，用于在qwen上使用grpo加强数学能力☆62May 14, 2025Updated last year
- Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL☆5,551Nov 13, 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...☆719Mar 28, 2026Updated 7 months ago
- Implement and train a Tiny LLM from scratch!☆23Jul 4, 2025Updated last year
- 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☆44Aug 27, 2024Updated 2 years ago
- 📚 从零开始构建大模型☆34,638Aug 8, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆22Oct 9, 2026Updated 3 weeks ago
- 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。☆22Sep 1, 2025Updated last year
- Official Implementation of Papar CM2☆27Apr 21, 2026Updated 6 months ago
- Recovering verbatim private reasoning from Claude extended-thinking signatures, with a local byte-exact verifier.☆21Aug 12, 2026Updated 2 months ago
- ☆44Nov 22, 2025Updated 11 months ago
- 包含了LLM的一些手撕代码，如强化学习。可以帮助从代码层面深入理解原理，以及有助于准备大模型面试可能出现的手撕。后续会更新Transformer等更多手撕☆138Mar 15, 2026Updated 7 months ago
- Awesome List for Agentic RL☆1,866Oct 21, 2026Updated last week