How is the data format organized when training llama?

choosewhatulike / trainable-agents

Code and datasets for "Character-LLM: A Trainable Agent for Role-Playing"

Apache License 2.0

429 stars 28 forks source link

Closed LeiyanGithub closed 8 months ago

LeiyanGithub commented 10 months ago

这种数据格式和vicuna类似的组织格式不一样呢，在执行的时候会报错

所以想请教一下，训练最终是不是应该组织成这种多轮的格式呢？

choosewhatulike commented 10 months ago

请用prompted/目录下的数据，已经format好了