XU-YIJIE / grpo-flat
Train your grpo with zero dataset and low resources, 8bit/4bit/lora/qlora supported, multi-gpu supported ...
☆69Updated last week
Alternatives and similar repositories for grpo-flat:
Users that are interested in grpo-flat are comparing it to the libraries listed below
- 使用单个24G显卡,从0开始训练LLM☆53Updated 5 months ago
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆187Updated 2 months ago
- From Llama to Deepseek, grpo/mtp implemented. With pt/sft/lora/qlora included☆26Updated 3 weeks ago
- ☆66Updated 6 months ago
- 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。☆83Updated 7 months ago
- ☆108Updated 9 months ago
- llm & rl☆102Updated this week
- 基于DPO算法微调语言大模型,简单好上手。☆37Updated 9 months ago
- The related works and background techniques about Openai o1☆219Updated 3 months ago
- 怎么训练一个LLM分词器☆144Updated last year
- SOTA RL fine-tuning solution for advanced math reasoning of LLM☆104Updated 2 weeks ago
- ☆38Updated 2 months ago
- Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models☆62Updated 2 months ago
- Reinforcement Learning in LLM and NLP.☆33Updated 3 weeks ago
- ☆78Updated 5 months ago
- ☆63Updated 4 months ago
- 通义千问的DPO训练☆46Updated 7 months ago
- RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.☆54Updated 2 months ago
- basic framework for rag(retrieval augment generation)☆83Updated last year
- ☆107Updated 5 months ago
- pytorch分布式训练☆65Updated last year
- ☆40Updated 8 months ago
- Scaling Deep Research via Reinforcement Learning in Real-world Environments.☆244Updated last week
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆115Updated last year
- ☆139Updated last year
- Official Repository for SIGIR2024 Demo Paper "An Integrated Data Processing Framework for Pretraining Foundation Models"☆74Updated 7 months ago
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆56Updated last year
- ☆67Updated last year
- This is a repo for showcasing using MCTS with LLMs to solve gsm8k problems☆72Updated last month
- ☆97Updated last year