Alternatives and similar repositories for grpo-flat

Users that are interested in grpo-flat are comparing it to the libraries listed below

• chunhuizhang / llm_rl
  llm & rl
  ☆156Updated this week
• yuanzhoulvpi2017 / SentenceEmbedding
  ☆111Updated last year
• akaihaoshuai / baby-llama2-chinese_cybertron
  使用单个24G显卡，从0开始训练LLM
  ☆56Updated last week
• percent4 / llm_math_solver
  本项目用于大模型数学解题能力方面的数据集合成，模型训练及评测，相关文章记录。
  ☆91Updated 10 months ago
• a-m-team / a-m-models
  a-m-team's exploration in large language modeling
  ☆173Updated last month
• yanqiangmiffy / how-to-train-tokenizer
  怎么训练一个LLM分词器
  ☆151Updated 2 years ago
• wjn1996 / Awesome-LLM-Reasoning-Openai-o1-Survey
  The related works and background techniques about Openai o1
  ☆223Updated 6 months ago
• HarderThenHarder / RLLoggingBoard
  A visuailzation tool to make deep understaning and easier debugging for RLHF training.
  ☆228Updated 4 months ago
• taishan1994 / pytorch-distributed-NLP
  pytorch分布式训练
  ☆67Updated last year
• RethinkFun / trian_ppo
  ☆86Updated 9 months ago
• Mxoder / LLM-from-scratch
  一些 LLM 方面的从零复现笔记
  ☆205Updated 2 months ago
• jackfsuia / nanoRLHF
  RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.
  ☆66Updated 4 months ago
• XU-YIJIE / hobo-llm-from-scratch
  From Llama to Deepseek, grpo/mtp implemented. With pt/sft/lora/qlora included
  ☆27Updated 2 months ago
• l294265421 / alpaca-rlhf
  Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat
  ☆114Updated 2 years ago
• yuanzhoulvpi2017 / nano_rl
  在verl上做reward的定制开发
  ☆70Updated last month
• Mryangkaitong / deepseek-r1-gsm8k
  ☆47Updated 5 months ago
• mindspore-lab / mindrlhf
  ☆36Updated 6 months ago
• Pillars-Creation / ChatGLM-RLHF-LoRA-RM-PPO
  ChatGLM-6B添加了RLHF的实现，以及部分核心代码的逐行讲解 ,实例部分是做了个新闻短标题的生成，以及指定context推荐的RLHF的实现
  ☆86Updated last year
• owenliang / qwen-dpo
  通义千问的DPO训练
  ☆50Updated 9 months ago
• hengjiUSTC / learn-llm
  ☆111Updated 8 months ago
• sugarandgugu / Simple-Trl-Training
  基于DPO算法微调语言大模型，简单好上手。
  ☆40Updated last year
• liujunwen23 / MIRE
  WWW2025 Multimodal Intent Recognition for Dialogue Systems Challenge
  ☆122Updated 8 months ago
• bytarnish / AGILE
  ☆147Updated 5 months ago
• suu990901 / LLaMA-MiLe-Loss
  Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models
  ☆64Updated 4 months ago
• tianyi-lab / Cherry_LLM
  [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…
  ☆378Updated 3 weeks ago
• lqtrung1998 / mwp_ReFT
  ☆543Updated 6 months ago
• km1994 / llms_paper
  该仓库主要记录 LLMs 算法工程师相关的顶会论文研读笔记（多模态、PEFT、小样本QA问答、RAG、LMMs可解释性、Agents、CoT）
  ☆343Updated last year
• THUDM / AlignBench
  大模型多维度中文对齐评测基准 (ACL 2024)
  ☆398Updated 11 months ago
• modelscope / Trinity-RFT
  Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…
  ☆136Updated this week
• stanleylsx / llms_tool
  一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测，低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。
  ☆217Updated last year