Alternatives and similar repositories for qwen2.5-0.5b-grpo

Users that are interested in qwen2.5-0.5b-grpo are comparing it to the libraries listed below

• chunhuizhang / llm_rl
  llm & rl
  ☆240Updated 2 weeks ago
• RethinkFun / trian_ppo
  ☆124Updated last year
• AI-Study-Han / Zero-Qwen-VL
  训练一个对中文支持更好的LLaVA模型，并开源训练代码和数据。
  ☆75Updated last year
• bobo0810 / LearnDeepSpeed
  DeepSpeed教程 & 示例注释 & 学习笔记 （大模型高效训练）
  ☆180Updated 2 years ago
• owenliang / qwen-dpo
  通义千问的DPO训练
  ☆56Updated last year
• wdndev / mllm_interview_note
  主要记录大语言大模型（LLMs） 算法（应用）工程师多模态相关知识
  ☆249Updated last year
• liangyuwang / zo2
  ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory [COLM2025]
  ☆192Updated 3 months ago
• yongliang-wu / DFT
  [Preprint] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.
  ☆490Updated 3 weeks ago
• qingkelab / qingketalk
  青稞Talk
  ☆157Updated 2 weeks ago
• RethinkFun / LLM
  ☆114Updated last year
• GAIR-NLP / MAYE
  Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
  ☆143Updated 7 months ago
• owenliang / bpe-tokenizer
  LLM Tokenizer with BPE algorithm
  ☆44Updated last year
• lzhxmu / CPPO
  CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models (NeurIPS 2025)
  ☆166Updated this week
• preacher-1 / MLA_tutorial
  from MHA, MQA, GQA to MLA by 苏剑林, with code
  ☆33Updated 8 months ago
• liujunwen23 / MIRE
  WWW2025 Multimodal Intent Recognition for Dialogue Systems Challenge
  ☆127Updated 11 months ago
• step-law / steplaw
  ☆205Updated last week
• juzhengz / LoRI
  [COLM 2025] LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
  ☆158Updated 4 months ago
• Alibaba-NLP / VRAG
  Repo for "VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforce…
  ☆389Updated 3 weeks ago
• aJupyter / ThinkLLM
  ThinkLLM：🚀 轻量、高效的大语言模型算法实现
  ☆106Updated 5 months ago
• waylandzhang / DeepSeek-RL-Qwen-0.5B-GRPO-gsm8k
  ☆85Updated 9 months ago
• Victorwz / Open-Qwen2VL
  [COLM 2025] Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources
  ☆280Updated 2 months ago
• swordlidev / Efficient-Multimodal-LLMs-Survey
  Efficient Multimodal Large Language Models: A Survey
  ☆375Updated 6 months ago
• phellonchen / Awesome-MLLM-Reasoning
  Latest Advances on Reasoning of Multimodal Large Language Models (Multimodal R1 \ Visual R1) ) 🍓
  ☆35Updated 7 months ago
• liangyuwang / Tiny-DeepSpeed
  Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library
  ☆48Updated 2 months ago
• dhcode-cpp / X-R1
  minimal-cost for training 0.5B R1-Zero
  ☆781Updated 5 months ago
• yuanzhoulvpi2017 / vscode_debug_transformers
  ☆395Updated 9 months ago
• qiufengqijun / open-r1-reprod
  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。
  ☆47Updated 6 months ago
• Alannikos / FunGPT
  In this fast-paced world, we all need a little something to spice up life. Whether you need a glass of sweet talk to lift your spirits or…
  ☆60Updated 5 months ago
• owenliang / pytorch-transformer
  pytorch复现transformer
  ☆86Updated last year
• chunhuizhang / pytorch_distribute_tutorials
  pytorch distribute tutorials
  ☆156Updated 4 months ago