这是一个open-r1的复现项目，对0.5B、1.5B、3B、7B的qwen模型进行GRPO训练，观察到一些有趣的现象。
☆63Apr 13, 2025Updated last year
Alternatives and similar repositories for open-r1-reprod
Users that are interested in open-r1-reprod are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Qwen2.5 0.5B GRPO☆86Feb 16, 2025Updated last year
- 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。☆867Feb 18, 2025Updated last year
- ☆26Nov 26, 2024Updated last year
- DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use☆29Mar 13, 2026Updated 5 months ago
- ☆16Sep 25, 2025Updated 11 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆12Jan 5, 2023Updated 3 years ago
- Repository for 3 papers on Summarization and Entailment for Medical User-Generated Questions.☆12Jun 7, 2022Updated 4 years ago
- Automatically exported from code.google.com/p/transducersaurus☆11Apr 1, 2015Updated 11 years ago
- ☆10May 23, 2022Updated 4 years ago
- kaggle:otto competition☆24Feb 13, 2023Updated 3 years ago
- Open-source repository for the OOPSLA'24 paper "CYCLE: Learning to Self-Refine Code Generation"☆10Mar 8, 2024Updated 2 years ago
- Repository for the Findings of ACL'23 paper Label Agnostic Pre-training for Zero-shot Text Classification☆13Aug 10, 2023Updated 3 years ago
- 收集整理大模型面试题☆12Aug 29, 2024Updated 2 years ago
- Train a tiny LLaMA model from scratch to repeat your words using Reinforcement Learning from Human Feedback (RLHF)☆18May 23, 2024Updated 2 years 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.
- code for EMNLP 2022 paper Better Few-Shot Relation Extraction with Label Prompt Dropout☆26Nov 8, 2024Updated last year
- 日期时间实体识别☆11Sep 10, 2020Updated 5 years ago
- ☆15Mar 30, 2025Updated last year
- ☆11Mar 5, 2024Updated 2 years ago
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆54Jul 15, 2025Updated last year
- ☆44Mar 6, 2025Updated last year
- Code space for L4DC paper "State-wise Safe Reinforcement Learning With Pixel Observations"☆11Apr 5, 2024Updated 2 years ago
- Code for ACM MM 2024 paper "A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoning"☆19Dec 5, 2024Updated last year
- Code for L4DC 2022 paper: Joint Synthesis of Safety Certificate and Safe Control Policy Using Constrained Reinforcement Learning.☆14Jul 31, 2023Updated 3 years 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.
- 基于ChatGLM3-6b的智能对话系统，集成了RAG、知识图谱、Agent、多模态等技术来增强大模型的回复质量。☆69Aug 12, 2024Updated 2 years ago
- A curated list of resources on on-policy distillation☆25Apr 13, 2026Updated 4 months ago
- [ICLR 2026] Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs☆47May 20, 2025Updated last year
- [ICLR 2025] Weighted-Reward Preference Optimization for Implicit Model Fusion☆14Mar 17, 2025Updated last year
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆504May 1, 2025Updated last year
- Documentation at☆14Mar 27, 2025Updated last year
- LLM 101: 一起入门大语言模型 课程网站☆15Feb 2, 2025Updated last year
- AlphaGo Zero Reinforcement Learning Sokoban Solver☆11Jun 20, 2018Updated 8 years ago
- ☆108Jul 24, 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.
- [ISSTA 2025] A Large-scale Empirical Study on Fine-tuning Large Language Models for Unit Testing☆13Feb 9, 2025Updated last year
- I-SHEEP: Iterative Self-enHancEmEnt Paradigm of LLMs through Self-Instruct and Self-Assessment☆17Jan 16, 2025Updated last year
- SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting☆29Jun 22, 2026Updated 2 months ago
- PipelineLLM 是一个系统性的大语言模型（LLM）后训练学习项目，涵盖从监督微调（SFT）到偏好优化（DPO）、强化学习（RLHF/PPO/GRPO）再到持续学习（Continual Learning)的完整技术栈。☆34Jan 16, 2026Updated 7 months ago
- A Code Efficiency Benchmark for Code Generation☆15May 26, 2025Updated last year
- Homeworks implementation of https://github.com/virginiakm1988/ML2022-Spring☆13Jan 28, 2023Updated 3 years ago
- MSRPAN: A Multiscale Residual Pyramid Attention Network for Medical Image Fusion☆14Nov 6, 2019Updated 6 years ago