jiangxinyang227 / LLM-tuning
llama,chatglm 等模型的微调
☆86Updated 8 months ago
Alternatives and similar repositories for LLM-tuning:
Users that are interested in LLM-tuning are comparing it to the libraries listed below
- deepspeed+trainer简单高效实现多卡微调大模型☆123Updated last year
- 中文 Instruction tuning datasets☆129Updated 11 months ago
- 使用 Qwen2ForSequenceClassification 简单实现文本分类任务。☆59Updated 9 months ago
- basic framework for rag(retrieval augment generation)☆82Updated last year
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆100Updated 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+☆92Updated last year
- ☆66Updated 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☆192Updated last year
- 怎么训练一个LLM分词器☆142Updated last year
- 大语言模型指令调优工具(支持 FlashAttention)☆171Updated last year
- 基于DPO算 法微调语言大模型,简单好上手。☆31Updated 8 months ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆106Updated last year
- ☆43Updated last year
- 使用单个24G显卡,从0开始训练LLM☆50Updated 4 months ago
- GoGPT:基于Llama/Llama 2训练的中英文增强大模型|Chinese-Llama2☆78Updated 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☆82Updated last year
- 使用qlora对中文大语言模型进行微调,包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE☆85Updated last year
- ☆160Updated last year
- moss chat finetuning☆50Updated 10 months ago
- T2Ranking: A large-scale Chinese benchmark for passage ranking.☆154Updated 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。☆116Updated 2 weeks ago
- 实现了Baichuan-Chat微调,Lora、QLora等各种微调方式,一键运行。☆70Updated last year
- BLOOM 模型的指令微调☆24Updated last year
- ☆134Updated 11 months ago
- 1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc☆162Updated last year
- 百川Dynamic NTK-ALiBi的代 码实现:无需微调即可推理更长文本☆47Updated last year
- ☆57Updated 2 years ago
- ☆104Updated 8 months ago
- Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models☆61Updated last month
- A simple framework for building some basic NLP tasks☆59Updated 2 years ago