linjh1118 / Llama3-Chinese-ORPOLinks
基于Llama3，通过进一步CPT，SFT，ORPO得到的中文版Llama3
☆17Updated last year
Alternatives and similar repositories for Llama3-Chinese-ORPO
Users that are interested in Llama3-Chinese-ORPO are comparing it to the libraries listed below
Sorting:
- pre-training llama3 using chinese☆13Updated last year
- （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。☆35Updated last year
- ☆16Updated last year
- the newest version of llama3，source code explained line by line using Chinese☆22Updated last year
- 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。☆44Updated 8 months ago
- Generate multi-round conversation roleplay data based on self-instruct and evol-instruct.☆134Updated 9 months ago
- 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…☆59Updated 4 months ago
- Copy the MLP of llama3 8 times as 8 experts , created a router with random initialization,add load balancing loss to construct an 8x8b Mo…☆27Updated last year
- A fluent, scalable, and easy-to-use LLM data processing framework.☆26Updated 2 months ago
- 集成Qwen与DeepSeek等先进大语言模型，支持纯LLM+分类层模式及LLM+LoRA+分类层模式，使用transformers模块化设计和训练便于根据需要调整或替换组件。☆14Updated last month
- 一起来养一只拥有专属记忆的AI猫猫吧！☆10Updated 11 months ago
- 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
- ☆94Updated last year
- 基于langchain设计的智能体任务，包含规划会话场景资源，构建子任务，任务执行器包含（MCTS）☆29Updated last week
- MetaSearch：llm深度研究（deepsearch）功能方案实现☆32Updated last month
- 超简单复现Deepseek-R1-Zero和Deepseek-R1，以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL，以激发LLM的自主验证反思能力。 About Clean, minimal, accessible reproduction of Dee…☆29Updated 6 months ago
- ☆95Updated 10 months ago
- Zero-human, cold-start construction of long-chain agents in professional domains☆41Updated 5 months ago
- 天池算法比赛《BetterMixture - 大模型数据混合挑战赛》的第一名top1解决方案☆32Updated last year
- 通义千问的DPO训练☆55Updated last year
- SUS-Chat: Instruction tuning done right☆49Updated last year
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆217Updated 2 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☆68Updated last year
- Collection of model-centric MCP servers☆23Updated 4 months ago
- 我们是第一个完全可商用的角色大模型。☆40Updated last year
- Official code for the paper: InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews (previo…☆86Updated 4 months ago
- 大语言模型训练和服务调研☆36Updated 2 years ago
- ☆44Updated 3 months ago
- Just for debug☆56Updated last year
- ☆42Updated 5 months ago