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。☆68Updated last year
- LLM for NER☆80Updated 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)☆314Updated last year
- basic framework for rag(retrieval augment generation)☆86Updated last year
- 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.☆291Updated 4 months ago
- 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
- Viscacha:通用信息抽取数据集收集☆27Updated last year
- 开源SFT数据集整理,随时补充☆562Updated 2 years ago
- CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models☆349Updated 6 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。☆126Updated 9 months ago
- 对llama3进行全参微调、lora微调以及qlora微调。☆211Updated last year
- 本项目使用大语言模型(LLM)进行开放领域三元组抽取。☆31Updated 2 years ago
- Universal information extraction with instruction learning☆393Updated 9 months ago
- Baichuan-13B 指令微调☆90Updated 2 years 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。☆220Updated 2 years ago
- Deepspeed、LLM、Medical_Dialogue、医疗大模型、预训练、微调☆287Updated last year
- [ACL 2024] IEPile: A Large-Scale Information Extraction Corpus☆208Updated 11 months ago
- ☆119Updated last year
- PromptCBLUE: a large-scale instruction-tuning dataset for multi-task and few-shot learning in the medical domain in Chinese☆383Updated last year
- 基于大语言模型的检索增强生成RAG示例☆167Updated 7 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…☆213Updated last year
- LAiW: A Chinese Legal Large Language Models Benchmark☆85Updated last year
- A simple, easy-to-hack GraphRAG implementation☆14Updated last year
- JurisLMs: Jurisprudential Language Models☆22Updated 2 years ago
- 使用 Qwen2ForSequenceClassification 简单实现文本分类任务。☆87Updated last year
- ☆76Updated 2 years ago
- 大模型文本分类☆91Updated 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.☆255Updated 2 years ago
- text embedding☆147Updated 2 years ago
- 快速入门RAG与私有化部署☆211Updated last year