XnneHang

XnneHang

github
steam_profiles
douban
HomeArchives作品集游戏

LLM

cover
cover
cover
cover
cover
cover

记录指令微调 Qwen-7B-Chat

写得有点随意，老师给了四个选题: YOLO 目标检测 - 6 class Unet 目标分割 - 3 class 大模型微调 基于 LSTM 的诗词续写. 前两个啥也学不到，第四个做 tokenize 和数据集清洗太麻烦了. 于是乎就顺势选了第三个，以前没做过…
LLM
Ownership of this blog data is guaranteed by blockchain and smart contracts to the creator alone.