jiahe7ay / MiniCharacterLLMLinks
这是一个一键让小参数大模型进行角色扮演的项目,从数据构成和训练都包含在这项目中
☆25Updated last year
Alternatives and similar repositories for MiniCharacterLLM
Users that are interested in MiniCharacterLLM are comparing it to the libraries listed below
Sorting:
- Alpaca Chinese Dataset -- 中文指令微调数据集☆209Updated 9 months ago
- 一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测,低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。☆217Updated last year
- A Multi-modal RAG Project with Dataset from Honor of Kings, one of the most popular smart phone games in China☆66Updated 10 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。☆91Updated 10 months ago
- 从0开始,将chatgpt的技术路线跑一遍。☆243Updated 10 months ago
- qwen models finetuning☆100Updated 4 months ago
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆452Updated 2 months ago
- 专注于中文领域大语言模型,落地到某个行业某个领域,成为一个行业大模型、公司级别或行业级别领域大模型。☆119Updated 4 months ago
- Firefly中文LLaMA-2大模型,支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型☆409Updated last year
- 【逐条处理完成】人为审核+修改每一条的弱智吧精选问题QA数据集☆210Updated 3 months ago
- ☆230Updated last year
- 阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理☆109Updated last year
- ☆111Updated last year
- The plan which extend ChatHaruhi into Zero-shot Roleplaying model☆108Updated last year
- 使用单个24G显卡,从0开始训练LLM☆56Updated last week
- 大语言模型指令调优工具(支持 FlashAttention)☆174Updated last year
- 想要从零开始训练一个中文的mini大语言模型,可以进行基本的对话,模型大小根据手头的机器决定☆60Updated 11 months ago
- ☆251Updated last month
- Baichuan-13B 指令微调☆90Updated 2 years ago
- 从小说中提取对话数据集☆217Updated last year
- 国内首个全参数训练的法律大模型 HanFei-1.0 (韩非)☆122Updated last year
- 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☆64Updated 5 months ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆108Updated last year
- ☆149Updated last year
- 怎么训练一个LLM分词器☆151Updated 2 years ago
- ☆65Updated last year
- 用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.☆253Updated last year
- 通义千问的DPO训练☆50Updated 9 months ago
- deep learning☆148Updated 2 months ago
- Generate multi-round conversation roleplay data based on self-instruct and evol-instruct.☆130Updated 6 months ago