liguodongiot / unify-easy-llm
unify-easy-llm(ULM)旨在打造一个简易的一键式大模型训练工具,支持Nvidia GPU、Ascend NPU等不同硬件以及常用的大模型。
☆23Updated last month
Related projects: ⓘ
- ☆22Updated last year
- 怎么训练一个LLM分词器☆123Updated last year
- 大模型/LLM推理和部署理论与实践☆35Updated last month
- 纯c++的全平台llm加速库,支持python调用,支持baichuan, glm, llama, moss基座,手机端流畅运行chatglm-6B级模型单卡可达10000+token / s,☆44Updated 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…☆159Updated 4 months ago
- 专注于Python/C++/CUDA、ML/DL/RL和NLP/KG/DS/LLM领域的技术分享。☆59Updated 2 months ago
- 快速入门RAG与私有化部署☆114Updated 5 months ago
- Train a Chinese LLM From 0 by Personal☆145Updated last week
- Imitate OpenAI with Local Models☆83Updated 3 weeks ago
- 演示 vllm 对中文大语言模型的神奇效果☆31Updated 10 months ago
- qwen-7b and qwen-14b finetuning☆82Updated 4 months ago
- large language model training-3-stages+deployment☆45Updated last year
- ☆196Updated 4 months ago
- 中文原生检索增强生成测评基准☆92Updated 5 months ago
- 大语言模型指令调优工具(支持 FlashAttention)☆162Updated 8 months ago
- 大语言模型训练和服务调研☆32Updated last year
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆107Updated last year
- Alpaca Chinese Dataset -- 中文指令微调数据集【人工+GPT4o持续更新】☆161Updated this week
- 一些 LLM 方面的从零复现笔记☆105Updated 3 months ago
- ChatGLM2-6B-Explained☆33Updated last year
- ☆15Updated 11 months ago
- ☆131Updated last week
- 百川Dynamic NTK-ALiBi的代码实现:无需微调即可推理更长文本☆45Updated last year
- 使用单个24G显卡,从0开始训练LLM☆47Updated 2 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆120Updated 9 months ago
- 部署你自己的OpenAI api🤩, 基于flask, transformers (使用 Baichuan2-13B-Chat-4bits 模型, 可以运行在单张Tesla T4显卡) ,实现了OpenAI中Chat, Models和Completions接口,包含流式响…☆85Updated 10 months ago
- 千问14B和7B的逐行解释☆46Updated 11 months ago
- 中文通用大模型开放域多轮测评基准 | An Open Domain Benchmark for Foundation Models in Chinese☆76Updated last year
- ☆104Updated 11 months ago
- 一个面向小白的大模型应用开发课程☆41Updated 10 months ago