CSHaitao / ChatGLM_mutli_gpu_tuning
deepspeed+trainer简单高效实现多卡微调大模型
☆121Updated last year
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
- 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
- 大语言模型指令调优工具(支持 FlashAttention)☆169Updated 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。☆115Updated 4 months ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆105Updated last year
- 怎么训练一个LLM分词器☆138Updated last year
- 中文 Instruction tuning datasets☆124Updated 9 months ago
- ☆159Updated last year
- llama,chatglm 等模型的微调☆85Updated 6 months ago
- Baichuan-13B 指令微调☆89Updated last year
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆100Updated 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.☆247Updated 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
- 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
- deep learning☆150Updated 7 months ago
- 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。☆206Updated last year
- llama信息抽取实战☆98Updated last year
- 国内首个全参数训练的法律大模型 HanFei-1.0 (韩非)☆112Updated last year
- MEASURING MASSIVE MULTITASK CHINESE UNDERSTANDING☆88Updated 10 months ago
- LAiW: A Chinese Legal Large Language Models Benchmark☆75Updated 6 months ago
- basic framework for rag(retrieval augment generation)☆81Updated 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+☆83Updated last year
- 中文大模型微调(LLM-SFT), 数学指令数据集MWP-Instruct, 支持模型(ChatGLM-6B, LLaMA, Bloom-7B, baichuan-7B), 支持(LoRA, QLoRA, DeepSpeed, UI, TensorboardX), 支持(微…☆183Updated 8 months ago
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆109Updated last year
- Baichuan2代码的逐行解析版本,适合小白☆211Updated last year
- 基于ChatGPT构建的中文self-instruct数据集☆113Updated last year
- make LLM easier to use☆59Updated last year
- ☆64Updated last year
- baichuan LLM surpervised finetune by lora☆61Updated last year
- ☆43Updated last year
- Deepspeed、LLM、Medical_Dialogue、医疗大模型、预训练、微调☆246Updated 7 months ago