VisRAG:把RAG扩展到图片和视觉
论文VisRAG: Vision-based Retrieval-Augmented Generation o […]
VisRAG:把RAG扩展到图片和视觉 Read More »
论文VisRAG: Vision-based Retrieval-Augmented Generation o […]
VisRAG:把RAG扩展到图片和视觉 Read More »
论文LLM in a flash: Efficient Large Language Model Infere
利用闪存(flash)存储模型参数并按需加载,在有限内存内运行大模型(LLMs) Read More »
论文Model Swarms: Collaborative Search to Adapt LLM Exper
模型群(Model Swarms),灵活组合多个LLM(大语言模型)专家的群体智能 Read More »
论文SANA: Efficient High-Resolution Image Synthesis with
SANA:一种用于生成高分辨率(最高可达4096×4096)的文本到图像生成框架 Read More »
论文FACTS About Building Retrieval Augmented Generation-b
“FACTS”框架:基于检索增强生成(RAG)的聊天机器人构建框架 Read More »
和客户交流,提到大模型不是搜索。大模型能够达成具有深度理解力的知识贯通。例如这个典型例子:网上刚看到一篇新闻,
大模型企业应用,Enterprise Applications of LLMs Read More »