morning-hao / domain-self-instruct
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
☆15Updated last year
Alternatives and similar repositories for domain-self-instruct:
Users that are interested in domain-self-instruct are comparing it to the libraries listed below
- 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。☆44Updated 8 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 3 weeks ago
- ☆134Updated 11 months ago
- basic framework for rag(retrieval augment generation)☆83Updated last year
- RAG 论文学习☆84Updated this week
- ☆105Updated 8 months ago
- 阿里天池: 2023全球智能汽车AI挑战赛——赛道一:AI大模型检索问答 baseline 80+☆92Updated last year
- ☆64Updated last year
- baichuan LLM surpervised finetune by lora☆62Updated last year
- ☆66Updated last year
- ☆160Updated last year
- [ACL 2024] IEPile: A Large-Scale Information Extraction Corpus☆189Updated 2 months ago
- 快速入门RAG与私有化部署☆163Updated 11 months ago
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆76Updated 4 months ago
- 怎么训练一个LLM分词器☆142Updated last year
- 大语言模型应用:RAG、NL2SQL、聊天机器人、预训练、MOE混合专家模型、微调训练、强化学习、天池数据竞赛☆58Updated last month
- Viscacha:通用信息抽取数据集收集☆26Updated last year
- 使用 Qwen2ForSequenceClassification 简单实现文本分类任务。☆59Updated 9 months ago
- llama信息抽取实战☆98Updated last year
- 大语言模型指令调优工具(支持 FlashAttention)☆171Updated 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.☆231Updated 3 months ago
- LLM for NER☆68Updated 7 months ago
- text embedding☆144Updated last year
- Baichuan-13B 指令微调☆89Updated 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.☆249Updated last year
- 基于大语言模型的检索增强生成RAG示例☆135Updated 3 months ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆106Updated last year
- llama,chatglm 等模型的微调☆86Updated 8 months ago
- LAiW: A Chinese Legal Large Language Models Benchmark☆78Updated 8 months ago
- ☆166Updated last year