open-chinese / alpaca-chinese-dataset
Alpaca Chinese Dataset -- 中文指令微调数据集
☆193Updated 5 months ago
Alternatives and similar repositories for alpaca-chinese-dataset:
Users that are interested in alpaca-chinese-dataset are comparing it to the libraries listed below
- 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…☆187Updated 10 months ago
- Baichuan2代码的逐行解析版本,适合小白☆212Updated last year
- Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型,支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.☆537Updated 8 months ago
- Firefly中文LLaMA-2大模型,支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型☆408Updated 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。☆213Updated last year
- ☆225Updated 10 months ago
- ☆134Updated 10 months ago
- 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。☆116Updated 2 weeks ago
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆409Updated 10 months ago
- qwen models finetuning☆93Updated 2 weeks ago
- 怎么训练一个LLM分词器☆142Updated last year
- 基于大语言模型的检索增强生成RAG示例☆134Updated 3 months ago
- ☆312Updated 9 months ago
- ☆306Updated last year
- 雅意信息抽取大模型:在百万级人工构造的高质量信息抽取数据上进行指令微调,由中科闻歌算法团队研发。 (Repo for YAYI Unified Information Extraction Model)☆295Updated 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。☆302Updated 8 months ago
- Imitate OpenAI with Local Models☆88Updated 6 months ago
- 活字通用大模型☆384Updated 6 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.☆249Updated last year
- 首个llama2 13b 中文版模型 (Base + 中文对话SFT,实现流畅多轮人机自然语言交互)☆90Updated last year
- 阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理☆85Updated 10 months ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆106Updated last year
- 中文书籍收录整理, Collection of Chinese Books☆179Updated last year
- Deepspeed、LLM、Medical_Dialogue、医疗大模型、预训 练、微调☆255Updated 9 months ago
- 大语言模型指令调优工具(支持 FlashAttention)☆171Updated last year
- A Chinese medical ChatGPT based on LLaMa, training from large-scale pretrain corpus and multi-turn dialogue dataset.☆343Updated last year
- 使用peft库,对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调,并做lora model和base model的merge及4bit的量化(quantize)。☆358Updated last year
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆400Updated last year
- 通义千问VLLM推理部署DEMO☆546Updated 11 months ago
- ☆192Updated last month