lansinuote / Simple_LLM_PPO
☆40Updated 8 months ago
Alternatives and similar repositories for Simple_LLM_PPO:
Users that are interested in Simple_LLM_PPO are comparing it to the libraries listed below
- 使用单个24G显卡，从0开始训练LLM☆53Updated 6 months ago
- ☆67Updated last year
- ChatGLM-6B添加了RLHF的实现，以及部分核心代码的逐行讲解 ,实例部分是做了个新闻短标题的生成，以及指定context推荐的RLHF的实现☆83Updated last year
- 大语言模型指令调优工具（支持 FlashAttention）☆172Updated last year
- 怎么训练一个LLM分词器☆144Updated 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.☆250Updated last year
- deepspeed+trainer简单高效实现多卡微调大模型☆125Updated last year
- ☆109Updated 10 months ago
- llama，chatglm 等模型的微调☆88Updated 9 months ago
- 一套代码指令微调大模型☆39Updated last year
- Qwen1.5-SFT(阿里, Ali), Qwen_Qwen1.5-2B-Chat/Qwen_Qwen1.5-7B-Chat微调(transformers)/LORA(peft)/推理☆60Updated 11 months ago
- pytorch分布式训练☆65Updated last year
- ☆71Updated 7 months ago
- Baichuan-13B 指令微调☆90Updated last year
- 2023全球智能汽车AI挑战赛——赛道一：AI大模型检索问答， 75+ baseline☆57Updated last year
- Generate dialog data from documents using LLM like ChatGLM2 or ChatGPT;利用ChatGLM2,ChatGPT等大模型根据文档生成对话数据集☆157Updated last year
- basic framework for rag(retrieval augment generation)☆84Updated last year
- ChatGLM2-6B-Explained☆35Updated last year
- 阿里天池: 2023全球智能汽车AI挑战赛——赛道一：AI大模型检索问答 baseline 80+☆101Updated last year
- 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。☆118Updated 2 months ago
- SuperCLUE-Math6：新一代中文原生多轮多步数学推理数据集的探索之旅☆54Updated last year
- 1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc☆161Updated last year
- 使用sentencepiece中BPE训练中文词表，并在transformers中进行使用。☆117Updated last year
- Baichuan2代码的逐行解 析版本，适合小白☆213Updated last year
- ☆34Updated 3 weeks ago
- 通义千问的DPO训练☆47Updated 7 months ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆107Updated last year
- 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☆30Updated 9 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
- baichuan LLM surpervised finetune by lora☆63Updated last year