lansinuote / Simple_TRLLinks
☆19Updated last year
Alternatives and similar repositories for Simple_TRL
Users that are interested in Simple_TRL are comparing it to the libraries listed below
Sorting:
- personal chatgpt☆384Updated 9 months ago
- 基于DPO算法微调语言大模型,简单好上手。☆45Updated last year
- ☆118Updated last year
- 通义千问的DPO训练☆55Updated last year
- 在verl上做reward的定制开发☆116Updated 4 months ago
- ☆110Updated 11 months ago
- Train your grpo with zero dataset and low resources, 8bit/4bit/lora/qlora supported, multi-gpu supported ...☆78Updated 4 months ago
- Reinforcement Learning in LLM and NLP.☆56Updated last week
- ☆100Updated 3 months ago
- 使用单个24G显卡,从0开始训练LLM☆55Updated 2 months ago
- ☆103Updated last year
- llm & rl☆218Updated last week
- ☆45Updated last year
- 阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理☆115Updated 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。☆95Updated last year
- 本项目是自动化学报中AUTOPLAN的代码地址,使用大语言模型完成了复杂任务的任务规划以及任务执行☆105Updated last week
- Inference code for LLaMA models☆123Updated 2 years ago
- 一些 LLM 方面的从零复现笔记☆221Updated 4 months ago
- ☆73Updated last year
- WWW2025 Multimodal Intent Recognition for Dialogue Systems Challenge☆126Updated 10 months ago
- ☆76Updated 4 months ago
- ☆84Updated 7 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。☆340Updated 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☆88Updated 2 years ago
- 该仓库主要记录 LLMs 算法工程师相关的顶会论文研读笔记(多模态、PEFT、小样本QA问答、RAG、LMMs可解释性、Agents、CoT)☆357Updated 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。☆219Updated last year
- LLM Tokenizer with BPE algorithm☆38Updated last year
- 怎么训练一个LLM分词器☆153Updated 2 years ago
- ☆115Updated 10 months ago
- Full stack LLM (Pre-training/finetuning, PPO(RLHF), Inference, Quant, etc.)☆27Updated 7 months ago