ITRECLab / Zh-MT-LLMLinks
中文海事大模型郑和(Zh-LLM)
☆19Updated last year
Alternatives and similar repositories for Zh-MT-LLM
Users that are interested in Zh-MT-LLM are comparing it to the libraries listed below
Sorting:
- ☆73Updated 3 months ago
- ☆58Updated last year
- ☆39Updated 6 months ago
- 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。☆97Updated last year
- 通义千问的DPO训练☆56Updated last year
- 训练一个对中文支持更好的LLaVA模型,并开源训练代码和数据。☆75Updated last year
- 从零到一实现了一个多模态大模型,并命名为Reyes(睿视),R:睿,eyes:眼。Reyes的参数量为8B,视觉编码器使用的是InternViT-300M-448px-V2_5,语言模型侧使用的是Qwen2.5-7B-Instruct,Reyes也通过一个两层MLP投影层连…☆26Updated 8 months ago
- ☆78Updated last year
- An interactive thinking and deep reasoning model. It provides a cognitive reasoning paradigm for complex multi-hop problems.☆69Updated 4 months ago
- ☆119Updated last year
- [ACL 2024] IEPile: A Large-Scale Information Extraction Corpus☆207Updated 10 months ago
- ☆23Updated 6 months ago
- 在verl上做reward的定制开发☆122Updated 5 months ago
- 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☆71Updated 9 months ago
- 一些大语言模型和多模态模型的生态,主要包括跨模态搜索、投机解码、QAT量化、多模态量化、ChatBot、OCR☆192Updated 2 months ago
- ☆265Updated 11 months ago
- ☆54Updated 8 months ago
- 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。☆67Updated last year
- Generate dialog data from documents using LLM like ChatGLM2 or ChatGPT;利用ChatGLM2,ChatGPT等大模型根据文档生成对话数据集☆160Updated 2 years ago
- Xtuner Factory☆34Updated last year
- 针对建筑规范文本数据的知识图谱实体关系提取,知识图谱构建,检索增强生成DEMO☆32Updated last year
- Code and Data for Our NeurIPS 2024 paper "AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback"☆33Updated last year
- [EMNLP2024] Aligning Large Language Models on Information Extraction☆53Updated last year
- Repo for for paper "AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction".☆72Updated last year
- 怎么训练一个LLM分词器☆154Updated 2 years ago
- ☆23Updated 10 months ago
- Official code for Dynamic Parametric RAG.☆159Updated 2 months ago
- 中文大语言模型评测第三期☆32Updated 2 months ago
- ☆234Updated last year
- Source code for our paper ''RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts''☆39Updated 5 months ago