shareAI-lab / alignment-handbook-cnLinks
中文版hf-alignment-handbook，大模型全套sft、dpo、orpo、cpt训练教程.
☆11Updated 10 months ago
Alternatives and similar repositories for alignment-handbook-cn
Users that are interested in alignment-handbook-cn are comparing it to the libraries listed below
Sorting:
- 最简易的R1结果在小模型上的复现，阐述类O1与DeepSeek R1最重要的本质。Think is all your need。利用实验佐证，对于强推理能力，think思考过程性内容是AGI/ASI的核心。☆45Updated 4 months ago
- LLM RAG 应用，支持 API 调用，语音交互。☆11Updated last year
- Real-time video understanding and interaction through text,audio,image and video with large multi-modal model. 利用多模态大模型的实时视频理解和交互框架，通过文本…☆23Updated last year
- Music large model based on InternLM2-chat.☆22Updated 6 months ago
- ☆12Updated 3 months ago
- ☆17Updated last year
- 基于Llama3，通过进一步CPT，SFT，ORPO得到的中文版Llama3☆17Updated last year
- (ICLR 2025) AgentRefine: Enhancing Agent Generalization through Refinement Tuning☆15Updated 4 months ago
- Built on the robust XTuner backend framework, XTuner Chat GUI offers a user-friendly platform for quick and efficient local model inferen…☆13Updated last year
- rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking☆38Updated 5 months ago
- ☆46Updated 2 months ago
- ☆15Updated last year
- Xtuner Factory☆33Updated last year
- In this fast-paced world, we all need a little something to spice up life. Whether you need a glass of sweet talk to lift your spirits or…☆58Updated 3 weeks ago
- MLLM @ Game☆14Updated last month
- Qwen1.5-SFT(阿里, Ali), Qwen_Qwen1.5-2B-Chat/Qwen_Qwen1.5-7B-Chat微调(transformers)/LORA(peft)/推理☆63Updated last year
- Awsome works based on SSM and Mamba☆17Updated last year
- SUS-Chat: Instruction tuning done right☆48Updated last year
- Official completion of “Training on the Benchmark Is Not All You Need”.☆34Updated 5 months ago
- Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory☆27Updated last year
- 集中管理所有的prompt。☆14Updated 7 months ago
- Finetune and Inference Qwen3-0.6B.☆15Updated last month
- ☆94Updated 6 months ago
- Train deepseek r1-like reasoning LLM with ease | 轻松训练1个deepseek r1类的推理LLM☆16Updated 4 months ago
- Pretrain、decay、SFT a CodeLLM from scratch 🧙♂️☆36Updated last year
- 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 last year
- MCP DeepResearch Server: 基于 LangGraph + Ollama + Tavily 的深度研究服务器，支持异步运行、超时控制与进度推送☆18Updated last week
- LLM+RAG for QA☆22Updated last year
- 一起来养一只拥有专属记忆的AI猫猫吧！☆10Updated 8 months ago
- 使用FastAPI+vLLM部署Qwen2.5☆19Updated 8 months ago