jiangxinyang227 / LLM-tuning
llama,chatglm 等模型的微调
☆79Updated 2 months ago
Related projects: ⓘ
- deepspeed+trainer简单高效实现多卡微调大模型☆115Updated 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+☆63Updated 8 months ago
- ☆156Updated last year
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆96Updated last year
- 怎么训练一个LLM分词器☆123Updated last year
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆107Updated last year
- basic framework for rag(retrieval augment generation)☆69Updated 8 months ago
- 使用qlora对中文大语言模型进行微调,包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE☆86Updated last year
- 大语言模型指令调优工具(支持 FlashAttention)☆162Updated 8 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☆75Updated last year
- MEASURING MASSIVE MULTITASK CHINESE UNDERSTANDING☆86Updated 5 months ago
- 使用单个24G显卡,从0开始训练LLM☆47Updated 2 months ago
- moss chat finetuning☆50Updated 4 months ago
- GoGPT:基于Llama/Llama 2训练的中英文增强大模型|Chinese-Llama2☆78Updated 11 months ago
- ☆90Updated 5 months ago
- 中文 Instruction tuning datasets☆112Updated 5 months ago
- ☆89Updated 9 months ago
- 基于 LoRA 和 P-Tuning v2 的 ChatGLM-6B 高效参数微调☆54Updated last year
- llama信息抽取实战☆95Updated last year
- 一套代码指令微调大模型☆36Updated 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。☆102Updated this week
- 百川Dynamic NTK-ALiBi的代码实现:无需微调即可推理更长文本☆45Updated last year
- ☆42Updated 9 months ago
- baichuan LLM surpervised finetune by lora☆57Updated last year
- NLU & NLG (zero-shot) depend on mengzi-t5-base-mt pretrained model☆75Updated 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☆186Updated last year
- [ACL 2024] IEPile: A Large-Scale Information Extraction Corpus☆154Updated 2 months ago
- make LLM easier to use☆59Updated last year
- 实现了Baichuan-Chat微调,Lora、QLora等各种微调方式,一键运行。☆70Updated last year
- ☆23Updated last year