lansinuote / Simple_TRL
☆18Updated 8 months ago
Alternatives and similar repositories for Simple_TRL:
Users that are interested in Simple_TRL are comparing it to the libraries listed below
- 基于DPO算法微调语言大模型,简单好上手。☆37Updated 9 months ago
- 使用单个24G显卡,从0开始训练LLM☆53Updated 5 months ago
- ☆66Updated last year
- ☆66Updated 6 months ago
- ☆108Updated 9 months ago
- Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models☆62Updated 2 months ago
- 包含程序员面试大厂面试题和面试经验☆124Updated 3 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☆82Updated last year
- Inference code for LLaMA models☆118Updated last year
- llama,chatglm 等模型的微调☆86Updated 9 months ago
- ☆40Updated 8 months ago
- ☆78Updated 5 months ago
- 对llama3进行全参微调 、lora微调以及qlora微调。☆192Updated 6 months ago
- 怎么训练一个LLM分词器☆144Updated last year
- ☆70Updated last month
- Train your grpo with zero dataset and low resources, 8bit/4bit/lora/qlora supported, multi-gpu supported ...☆69Updated last week
- 通义千问的DPO训练☆46Updated 7 months ago
- ☆139Updated last year
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆115Updated last year
- 阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理☆92Updated 11 months ago
- 使用LoRA对Chinese-LLaMA-Alpaca进行微调。☆35Updated last year
- 大模型基础学习和面试八股文☆108Updated last year
- 本项目用于大模型数学解题能力方面的数据集合成,模型训练及评测,相关文章记录。☆83Updated 7 months ago
- The Role Playing Project of Honor-of-Kings Based on LnternLM2。峡谷小狐仙--王者荣耀领域的角色扮演聊天机器人,结合多模态技术将英雄妲己的形象带入大模型中。☆23Updated 8 months ago
- This is a detailed code demo on how to conduct Full-Param Supervised Fine-tuning (SFT) and DPO (Direct Preference Optimization)☆13Updated 3 months ago
- 欢迎来到 "LLM-travel" 仓库!探索大语言模型(LLM)的奥秘 🚀。致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用。☆314Updated 9 months ago
- 训练一个对中文支持更好的LLaVA模型,并开源训练代码和数据。☆54Updated 7 months ago
- Reinforcement Learning in LLM and NLP.☆33Updated 3 weeks ago
- ☆66Updated 8 months ago
- personal chatgpt☆361Updated 4 months ago