waylandzhang / Transformer-from-scratchLinks
☆489Updated last year
Alternatives and similar repositories for Transformer-from-scratch
Users that are interested in Transformer-from-scratch are comparing it to the libraries listed below
Sorting:
- 从零实现一个 llama3 中文版☆998Updated last year
- 从零实现一个小参数量中文大语言模型。☆904Updated last year
- 从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)☆505Updated 9 months ago
- 本项目为书籍《大模型RAG实战》的代码以及资料汇总。☆265Updated last year
- 一个基于langchain实现RAG的简单示例☆594Updated 6 months ago
- Llama3-Tutorial(XTuner、LMDeploy、OpenCompass)☆511Updated last year
- DeepSeek 系列工作解读、扩展和复现。☆691Updated 8 months ago
- 《Reinforcement Learning》读书学习与视频分享笔记☆69Updated 8 months ago
- 大模型/LLM推理和部署理论与实践☆368Updated 5 months ago
- Learning Large Language Model (LLM)(大语言模型学习)☆860Updated 8 months ago
- 《大模型项目实战:多领域智能应用开发》配套资源☆214Updated last month
- Learning LLM Implementaion and Theory for Practical Landing☆191Updated 11 months ago
- LLM全栈优质资源汇总☆663Updated 5 months ago
- 通过带领大家解读Transformer模型来加深对模型的理解☆230Updated 6 months ago
- 尝试自己从头写一个LLM,参考llama和nanogpt☆68Updated last year
- 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。☆706Updated 10 months ago
- 从零到一实现一个 miniLLM~(动手学习LLM)☆76Updated last year
- 从0开始,将chatgpt的技术路线跑一遍。☆268Updated last year
- 复现大模型相关算法及一些学习记录☆2,713Updated last week
- 大语言模型微调,Qwen2VL、Qwen2、GLM4指令微调☆578Updated 6 months ago
- ☆350Updated 7 months ago
- Chat-甄嬛是利用《甄嬛传》剧本中所有关于甄嬛的台词和语句,基于ChatGLM2进行LoRA微调得到的模仿甄嬛语气的聊天语言模型。☆776Updated 7 months ago
- A comprehensive library for implementing LLMs, including a unified training pipeline and comprehensive model evaluation.☆847Updated 6 months ago
- Huggingface transformers的中文文档☆284Updated 2 years ago
- AGI资料汇总学习(主要包括LLM和AIGC),持续更新......☆459Updated 3 weeks ago
- A simple and trans-platform agent framework and tutorial☆198Updated this week
- 中文翻译的 Hands-On-Large-Language-Models (hands-on-llms),动手学习大模型☆1,938Updated 2 months ago
- 一些 LLM 方面的从零复现笔记☆241Updated 7 months ago
- TinyRAG☆383Updated 5 months ago
- 异步图书:《 GPT图解 大模型是怎样构建的》- 这套代码是AI Coder出现之前,自己用纯手工搭建的一套简单有效的NLP经典算法集合。在大语言模型推动的AI Coder兴起之后,很少有机会再创作这么有“手工风”的代码了,不知道这是值得开心还是值得遗憾的事情。☆188Updated last year