CSHaitao / ChatGLM_mutli_gpu_tuningLinks
deepspeed+trainer简单高效实现多卡微调大模型
☆126Updated 2 years ago
Alternatives and similar repositories for ChatGLM_mutli_gpu_tuning
Users that are interested in ChatGLM_mutli_gpu_tuning are comparing it to the libraries listed below
Sorting:
- 大语言模型指令调优工具(支持 FlashAttention)☆173Updated last year
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆108Updated last year
- llama,chatglm 等模型的微调☆89Updated 11 months ago
- 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☆86Updated last year
- 对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF☆195Updated 2 years ago
- ☆162Updated 2 years ago
- 怎么训练一个LLM分词器☆150Updated last year
- Baichuan-13B 指令微调☆90Updated 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 3 months ago
- ☆43Updated last year
- 使用qlora对中文大语言模型进行微调,包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE☆87Updated 2 years ago
- Baichuan2代码的逐行解析版本,适合小白☆214Updated last year
- llama信息抽取实战☆100Updated 2 years ago
- 实现了Baichuan-Chat微调,Lora、QLora等各种微调方式,一键运行。☆71Updated last year
- 基于 LoRA 和 P-Tuning v2 的 ChatGLM-6B 高效参数微调☆55Updated 2 years ago
- MEASURING MASSIVE MULTITASK CHINESE UNDERSTANDING☆87Updated 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.☆252Updated last year
- basic framework for rag(retrieval augment generation)☆85Updated last year
- baichuan LLM surpervised finetune by lora☆63Updated 2 years ago
- LAiW: A Chinese Legal Large Language Models Benchmark☆80Updated 11 months ago
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆114Updated 2 years ago
- 中文 Instruction tuning datasets☆132Updated last year
- moss chat finetuning☆50Updated last year
- make LLM easier to use☆59Updated last year
- ☆112Updated 11 months ago
- Implementation of Chinese ChatGPT☆285Updated last year
- 微调ChatGLM☆126Updated 2 years ago
- 1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc☆160Updated last year
- ☆63Updated 2 years ago
- ☆70Updated last year