mindspore-lab / mindrlhfLinks
☆36Updated 7 months ago
Alternatives and similar repositories for mindrlhf
Users that are interested in mindrlhf are comparing it to the libraries listed below
Sorting:
- ☆83Updated last year
- 怎么训练一个LLM分词器☆151Updated 2 years ago
- 大模型多维度中文对齐评测基准 (ACL 2024)☆398Updated 11 months ago
- ☆111Updated 8 months ago
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆114Updated 2 years ago
- A flexible and efficient training framework for large-scale alignment tasks☆388Updated last week
- ☆169Updated last week
- Collaborative Training of Large Language Models in an Efficient Way☆416Updated 10 months ago
- ☆172Updated last year
- Efficient, Low-Resource, Distributed transformer implementation based on BMTrain☆257Updated 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。☆217Updated last year
- ☆307Updated 2 years ago
- Implementation of Chinese ChatGPT☆285Updated last year
- 使用单个24G显卡,从0开始训练LLM☆56Updated last week
- 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。☆329Updated 11 months ago
- ☆52Updated 2 years ago
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆228Updated 4 months ago
- Train your grpo with zero dataset and low resources, 8bit/4bit/lora/qlora supported, multi-gpu supported ...☆74Updated 2 months ago
- ☆17Updated 2 years ago
- 中文 Instruction tuning datasets☆132Updated last year
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆223Updated last year
- 大语言模型指令调优工具(支持 FlashAttention)☆174Updated last year
- OpenLLMWiki: Docs of OpenLLMAI. Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXi…☆260Updated 7 months ago
- ☆281Updated 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。☆119Updated 4 months ago
- Naive Bayes-based Context Extension☆326Updated 7 months ago
- 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.☆253Updated 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。☆91Updated 10 months ago
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆97Updated last year
- The Roadmap for LLMs☆85Updated last year