lansinuote / Simple_RLHF_Llama3Links
☆33Updated last year
Alternatives and similar repositories for Simple_RLHF_Llama3
Users that are interested in Simple_RLHF_Llama3 are comparing it to the libraries listed below
Sorting:
- ☆109Updated 7 months ago
- ☆85Updated 11 months ago
- 一些 LLM 方面的从零复现笔记☆241Updated 8 months ago
- personal chatgpt☆403Updated last year
- 在verl上做reward的定制开发☆140Updated 7 months ago
- ☆82Updated last month
- 对llama3进行全参微调、lora微调以及qlora微调。☆212Updated last year
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆486Updated 8 months ago
- ☆23Updated 8 months ago
- ☆119Updated last year
- 通义千问的DPO训练☆61Updated last year
- llm & rl☆266Updated 2 months ago
- 欢迎来到 "LLM-travel" 仓库!探索大语言模型(LLM)的奥秘 🚀。致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用。☆364Updated last year
- 从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)☆513Updated 9 months ago
- Train a 1B LLM with 1T tokens from scratch by personal☆782Updated 8 months ago
- 从0开始,将chatgpt的技术路线跑一遍。☆271Updated last year
- kaggle 2024 Eedi 第10名 金牌方案☆44Updated last year
- TinyRAG☆398Updated 6 months ago
- LLM Tokenizer with BPE algorithm☆46Updated last year
- ☆125Updated last year
- 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。☆99Updated last year
- 快速入门RAG与私有化部署☆212Updated last year
- Huggingface transformers的中文文档☆285Updated 2 years ago
- 欢迎来到 LLM-Dojo,这里是一个开源大模型学习场所,使用简洁且易阅读的代码构建模型训练框架(支持各种主流模型如Qwen、Llama、GLM等等)、RLHF框架(DPO/CPO/KTO/PPO)等各种功能。👩🎓👨🎓☆913Updated last month
- DeepSeek 系列工作解读、扩展和复现。☆699Updated 9 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☆74Updated 11 months ago
- everything about llm & aigc☆108Updated 3 weeks ago
- 使用单个24G显卡,从0开始训练LLM☆56Updated 6 months ago
- 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。☆716Updated 10 months ago
- ☆115Updated last year