ITRECLab / Zh-MT-LLMLinks
中文海事大模型郑和(Zh-LLM)
☆17Updated 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:
- ☆40Updated last month
- 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。☆61Updated 9 months ago
- YiZhao: A 2TB Open Financial Corpus. Data and tools for generating and inspecting YiZhao, a safe, high-quality, open-source bilingual fin…☆26Updated 6 months ago
- 在verl上做reward的定制开发☆56Updated last month
- 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☆62Updated 4 months ago
- 通义千问的DPO训练☆49Updated 9 months ago
- Xtuner Factory☆33Updated last year
- ☆112Updated 11 months ago
- ☆36Updated 2 months ago
- ☆57Updated 8 months ago
- ☆23Updated last month
- LLM+RAG for QA☆21Updated last year
- Code and data for QueryAgent(ACL 2024)☆21Updated 6 months ago
- the newest version of llama3,source code explained line by line using Chinese☆22Updated last year
- 用大模型批量处理数据,现支持各种大模型做OCR,支持通义千问, 月之暗面, 百度飞桨OCR, OpenAI 和LLAVA。Use LLM to generate or clean data for academic use. Support OCR with qwen, m…☆14Updated 9 months ago
- 本项目使用大语言模型(LLM)进行开放领域三元组抽取。☆26Updated last year
- TianGong-AI-Unstructure☆68Updated 2 weeks ago
- Repo for for paper "AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction".☆67Updated 11 months ago
- A Toolkit for Table-based Question Answering☆112Updated last year
- CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation☆53Updated last month
- 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
- 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。☆56Updated 11 months ago
- ☆23Updated 2 months ago
- The first Chinese Multimodal Medical Knowledge Graph☆41Updated 2 years ago
- [EMNLP2024] Aligning Large Language Models on Information Extraction☆50Updated 7 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☆86Updated last year
- ☆67Updated last month
- A Chinese National Medical Licensing Examination dataset and large languge model benchmarks☆67Updated 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…☆14Updated 4 months ago
- (ICLR'25) A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents☆70Updated 4 months ago