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
- ChatGLM2-6B微 调, SFT/LoRA, instruction finetune☆107Updated 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
- 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
- deepspeed+trainer简单高效实现多卡微调大模型☆123Updated 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 last month
- GoGPT:基于Llama/Llama 2训练的中英文增强大模型|Chinese-Llama2☆78Updated last year
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆99Updated last year
- baichuan LLM surpervised finetune by lora☆63Updated last year
- ☆160Updated 2 years ago
- 大语言模型指令调优工具(支持 FlashAttention)☆172Updated last year
- basic framework for rag(retrieval augment generation)☆83Updated last year
- 中文 Instruction tuning datasets☆128Updated last year
- A repo for update and debug Mixtral-7x8B、MOE、ChatGLM3、LLaMa2、 BaChuan、Qwen an other LLM models include new models mixtral, mixtral 8x7b, …☆43Updated last month
- moss chat finetuning☆50Updated 11 months ago
- NLU & NLG (zero-shot) depend on mengzi-t5-base-mt pretrained model☆75Updated 2 years ago
- 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
- llama信息抽取实战☆98Updated 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+☆98Updated last year
- 怎么训练一个LLM分词器☆144Updated last year
- LLM for NER☆68Updated 8 months ago
- 基于 LoRA 和 P-Tuning v2 的 ChatGLM-6B 高效参数微调☆55Updated last year
- ☆66Updated last year
- 使用 Qwen2ForSequenceClassification 简单实现文本分类任务。☆59Updated 10 months ago
- MEASURING MASSIVE MULTITASK CHINESE UNDERSTANDING☆87Updated last year
- ☆107Updated 9 months ago
- ☆139Updated last year
- Baichuan-13B 指令微调☆89Updated last year
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆115Updated last year
- ☆43Updated last year
- 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。☆214Updated last year