shareAGI / alignment-handbook-cn
中文版hf-alignment-handbook，大模型全套sft、dpo、orpo、cpt训练教程.
☆11Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for alignment-handbook-cn
- Built on the robust XTuner backend framework, XTuner Chat GUI offers a user-friendly platform for quick and efficient local model inferen…☆11Updated 9 months ago
- 基于Llama3，通过进一步CPT，SFT，ORPO得到的中文版Llama3☆17Updated 6 months ago
- ☆13Updated 4 months ago
- （撰写ing..)本仓库偏教程性质，以「模型中文化」为一个典型的模型训练问题切入场景，指导读者上手学习LLM二次微调训练。☆29Updated 3 months ago
- 通义千问的DPO训练☆27Updated last month
- Qwen-WisdomVast is a large model trained on 1 million high-quality Chinese multi-turn SFT data, 200,000 English multi-turn SFT data, and …☆18Updated 7 months ago
- ☆16Updated 3 months ago
- the newest version of llama3，source code explained line by line using Chinese☆22Updated 6 months ago
- SUS-Chat: Instruction tuning done right☆47Updated 9 months ago
- rwkv finetuning☆35Updated 6 months ago
- LLM RAG 应用，支持 API 调用，语音交互。☆10Updated 4 months ago
- Repo for for paper "AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction".☆50Updated 3 months ago
- ✅4g GPU可用 | 简易实现ChatGLM单机调用多个计算设备（GPU、CPU）进行推理☆34Updated last year
- LLM+RAG for QA☆19Updated 9 months ago
- Music large model based on InternLM2-chat.☆21Updated 3 months ago
- 实现Blip2RWKV+QFormer的多模态图文对话大模型，使用Two-Step Cognitive Psychology Prompt方法，仅3B参数的模型便能够出现类人因果思维链。对标MiniGPT-4，ImageBind等图文对话大语言模型，力求以更小的算力和资源实…☆36Updated last year
- Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory☆25Updated 6 months ago
- Gemma-SFT, gemma-2b/gemma-7b微调(finetune,transformers)/LORA(peft)/推理(inference)☆27Updated 5 months ago
- 探索 LLM 在法律行业的应用潜力☆24Updated this week
- 用大模型批量处理数据，现支持各种大模型做OCR，支持通义千问, 月之暗面, 百度飞桨OCR, OpenAI 和LLAVA。Use LLM to generate or clean data for academic use. Support OCR with qwen, m…☆9Updated last month
- Its an open source LLM based on MOE Structure.☆57Updated 4 months ago
- 通用简单工具项目☆13Updated last month
- 我们是第一个完全可商用的角色大模型。☆35Updated 3 months ago
- ModelScope+Transformers+SwanLab实现Qwen-1.5-7b的指令微调任务☆10Updated 5 months ago
- 纯c++的全平台llm加速库，支持python调用，支持chatglm-6B, llama, baichuan, moss基座，x86 / ARM☆9Updated 3 months ago
- Qwen1.5-SFT(阿里, Ali), Qwen_Qwen1.5-2B-Chat/Qwen_Qwen1.5-7B-Chat微调(transformers)/LORA(peft)/推理☆44Updated 5 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。☆52Updated 2 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
- VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle various visual tasks.☆181Updated this week
- 使用langchain实现 故事情景生成，情感情景引导，剧情总结，性格分析☆14Updated 5 months ago