RethinkFun / trian_ppo
☆13Updated last month
Related projects ⓘ
Alternatives and complementary repositories for trian_ppo
- ☆16Updated 3 months ago
- 通义千问的DPO训练☆27Updated 2 months ago
- ☆37Updated 3 months ago
- 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。☆38Updated 2 months ago
- 本项目是自动化学报中AUTOPLAN的代码 地址,使用大语言模型完成了复杂任务的任务规划以及任务执行☆80Updated last week
- ☆49Updated this week
- 使用单个24G显卡,从0开始训练LLM☆49Updated 3 weeks ago
- A Multi-modal RAG Project with Dataset from Honor of Kings, one of the most popular smart phone games in China☆51Updated 2 months ago
- Music large model based on InternLM2-chat.☆21Updated 4 months ago
- ☆22Updated last year
- Generate dialog data from documents using LLM like ChatGLM2 or ChatGPT;利用ChatGLM2,ChatGPT等大模型根据文档生成对话数据集☆140Updated last year
- pretrain a wiki llm using transformers☆10Updated 2 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。☆55Updated 2 months ago
- 大语言模型应用:RAG、NL2SQL、聊天机器人、预训练、MOE混合专家模型、微调训练、强化学习、天池数据竞赛☆48Updated 5 months ago
- LLM Tokenizer with BPE algorithm☆27Updated 6 months ago
- 大模型检索增强生成技术最佳实践。☆46Updated 2 months ago
- The Role Playing Project of Honor-of-Kings Based on LnternLM2。峡谷小狐仙--王者荣耀领域的角色扮演聊天机器人,结合多模态技术将英雄妲己的形象带入大模型中。☆19Updated 3 months ago
- ☆13Updated 5 months ago
- ☆85Updated last week
- ☆129Updated 4 months ago
- WWW2025 Multimodal Intent Recognition for Dialogue Systems Challenge☆59Updated last week
- 🎓Automatically Update agent Papers Daily using Github Actions (Update Every 12th hours)☆19Updated this week
- 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☆78Updated last year
- ☆26Updated this week
- 快速入门RAG与私有化部署☆131Updated 7 months ago
- Psychological Counselor's Digital Twin Framework(心理咨询师数字孪生框架)☆43Updated 2 months ago
- 从0开始,将chatgpt的技术路线跑一遍。☆152Updated 2 months ago
- 个人项目地址,一些大语言模型和多模态模型的应用☆123Updated 2 weeks ago
- 一些 LLM 方面的从零复现笔记☆137Updated 2 months ago