Pillars-Creation / ChatGLM-RLHF-LoRA-RM-PPOLinks
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
☆85Updated last year
Alternatives and similar repositories for ChatGLM-RLHF-LoRA-RM-PPO
Users that are interested in ChatGLM-RLHF-LoRA-RM-PPO are comparing it to the libraries listed below
Sorting:
- deepspeed+trainer简单高效实现多卡微调大模型☆125Updated 2 years ago
- 对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF☆194Updated 2 years ago
- ☆110Updated 11 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。☆217Updated last year
- ☆69Updated last year
- baichuan LLM surpervised finetune by lora☆63Updated last year
- Baichuan-13B 指令微调☆90Updated last year
- 怎么训练一个LLM分词器☆149Updated 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 2 months ago
- Baichuan2代码的逐行解析版本,适合小白☆214Updated 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…☆201Updated last year
- 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
- 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.☆251Updated last year
- 阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理☆104Updated last year
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆101Updated last year
- 基于 LoRA 和 P-Tuning v2 的 ChatGLM-6B 高效参数微调☆55Updated 2 years ago
- ☆162Updated 2 years ago
- 对llama3进行全参微调、lora微调以及qlora微调。☆198Updated 8 months ago
- basic framework for rag(retrieval augment generation)☆84Updated last year
- 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
- ☆141Updated last year
- llama2 finetuning with deepspeed and lora☆174Updated last year
- llama,chatglm 等模型的微调☆89Updated 10 months ago
- 使用LoRA对Chinese-LLaMA-Alpaca进行微调。☆34Updated 2 years ago
- A full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Huma…☆135Updated 2 years ago
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆115Updated 2 years ago
- 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+☆105Updated last year
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆79Updated 6 months ago
- pytorch分布式训练☆66Updated last year