音乐播放 Posted on 2023-02-20 Edited on 2023-02-25 Waline: Word count in article: 743 Reading time ≈ 1 mins. ヾ(≧▽≦*)o music by @fortunato Read more »
开源仓库问答机器人——基于LLM+Langchain+streamlit开发 Posted on 2024-12-03 In LLM Waline: Word count in article: 28k Reading time ≈ 25 mins. 应用场景说明以Vchart为例,开发一个开源仓库问答机器人。 背景 Read more »
视频生成实践 Posted on 2024-04-24 In 论文阅读 , AIGC Waline: Word count in article: 4.2k Reading time ≈ 4 mins. 视频生成实践依照开源代码部署模型,实现文生视频/图生视频。以下仓库为记录存储几种视频生成方法: https://github.com/Xandra298/VideoGen 其中,I2VGen-XL和text-to-video-synthesis论文大体介绍如下。 Read more »
RAG with Gemma using wikipedia api Posted on 2024-04-23 In LLM Waline: Word count in article: 11k Reading time ≈ 10 mins. 运行环境: windows11 CPU 12th Gen Intel(R) Core(TM) i5-12500H 运行内存16G Gemma:轻量级LLM 基于langchain实现,可视化使用smith.langchain Setup Read more »
Retrieval Augmented Generation (RAG) Posted on 2024-04-22 In LLM Waline: Word count in article: 6.6k Reading time ≈ 6 mins. What is RAG Motivation: challenges when working with LLMs,such as domain knowledge gaps, factuality issues, and hallucination(幻觉). Retrieval Augmented Generation (RAG) 通过引入外部知识源来增强LLMs以缓解上述问题,augmenting LLMs with external knowledge such as databases. 一个关键的优势是RAG方法不需要为任务特定的应用重新训练LLM RAG can help reduce issues of hallucination or performance when addressing problems in a highly evolving environment. 定义 Read more »