kanhaoning / RAG-Optimization-PracticesLinks
☆66Updated 2 months ago
Alternatives and similar repositories for RAG-Optimization-Practices
Users that are interested in RAG-Optimization-Practices are comparing it to the libraries listed below
Sorting:
- 1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc☆161Updated 2 months ago
- ☆118Updated last year
- code for piccolo embedding model from SenseTime☆140Updated last year
- 使用 Qwen2ForSequenceClassification 简单实现文本分类任务。☆82Updated last year
- 大语言模型指令调优工具(支持 FlashAttention)☆178Updated last year
- ☆39Updated 5 months ago
- ☆145Updated last year
- 怎么训练一个LLM分词器☆153Updated 2 years ago
- 通义千问的DPO训练☆55Updated last year
- 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。☆63Updated last year
- 通用简单工具项目☆20Updated last year
- 本项目用于大模型数学解题能力方面的数据集合成,模型训练及评测,相关文章记录。☆95Updated last year
- ☆176Updated 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。☆123Updated 7 months ago
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆89Updated 10 months ago
- [ACL 2024] IEPile: A Large-Scale Information Extraction Corpus☆203Updated 8 months ago
- 中文预训练ModernBert☆85Updated 5 months ago
- deepResearch☆72Updated 5 months ago
- ☆232Updated last year
- Qwen-WisdomVast is a large model trained on 1 million high-quality Chinese multi-turn SFT data, 200,000 English multi-turn SFT data, and …☆18Updated last year
- ☆28Updated 11 months ago
- ☆163Updated 2 years ago
- Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models☆65Updated 7 months ago
- ☆98Updated last year
- 使用单个24G显卡,从0开始训练LLM☆55Updated 2 months ago
- ☆68Updated 2 years ago
- 中文原生检索增强生成测评基准☆123Updated last year
- basic framework for rag(retrieval augment generation)☆85Updated last year
- Llama-3-SynE: A Significantly Enhanced Version of Llama-3 with Advanced Scientific Reasoning and Chinese Language Capabilities | 继续预训练提升 …☆34Updated 4 months 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)☆310Updated last year