morning-hao / domain-self-instructLinks
受到self-instruct启发,除了通用LLM还能做垂直领域的小LLM实现定制效果，通过GPT获得question和answer来作为训练数据
☆18Updated 2 years ago
Alternatives and similar repositories for domain-self-instruct
Users that are interested in domain-self-instruct are comparing it to the libraries listed below
Sorting:
- 本项目用于Embedding模型的相关实验，包括Embedding模型评估、Embedding模型微调、Embedding模型量化等。☆61Updated 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。☆122Updated 6 months ago
- 本项目是针对RAG中的Retrieve阶段的召回技术及算法效果所做评估实验。使用主体框架为LlamaIndex.☆277Updated last month
- 开源SFT数据集整理,随时补充☆540Updated 2 years ago
- basic framework for rag(retrieval augment generation)☆86Updated last year
- ☆145Updated last year
- CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models☆330Updated 3 months ago
- Baichuan-13B 指令微调☆91Updated 2 years ago
- text embedding☆147Updated last year
- Viscacha：通用信息抽取数据集收集☆26Updated last year
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆389Updated 2 months ago
- 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
- 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☆87Updated 2 years ago
- Deepspeed、LLM、Medical_Dialogue、医疗大模型、预训练、微调☆279Updated last year
- 使用 Qwen2ForSequenceClassification 简单实现文本分类任务。☆83Updated last year
- ☆163Updated 2 years ago
- 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)☆308Updated last year
- 怎么训练一个LLM分词器☆152Updated 2 years ago
- Universal information extraction with instruction learning☆391Updated 6 months ago
- ☆115Updated last year
- PromptCBLUE: a large-scale instruction-tuning dataset for multi-task and few-shot learning in the medical domain in Chinese☆378Updated last year
- 大语言模型指令调优工具（支持 FlashAttention）☆179Updated last year
- LAiW: A Chinese Legal Large Language Models Benchmark☆83Updated last year
- ☆67Updated 2 years ago
- 对llama3进行全参微调、lora微调以及qlora微调。☆208Updated 11 months ago
- ☆34Updated 2 months ago
- 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…☆210Updated last year
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆102Updated 2 years ago
- 中文 Instruction tuning datasets☆135Updated last year
- 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.☆254Updated 2 years ago