关于Chinese-Vicuna-medical的continuous-finetune疑问

Facico / Chinese-Vicuna

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

https://github.com/Facico/Chinese-Vicuna

Apache License 2.0

4.14k stars 421 forks source link

Closed yuelinan closed 1 year ago

yuelinan commented 1 year ago

您好，请问您在对医学数据进行continuous-finetune的时候，是否是将医学数据和之前通用领域的数据合并进行continuous-finetune？还是在使用checkpoint-11600保存参数的基础上，用医学数据进行continuous-finetune？

Facico commented 1 year ago

并没有合并，直接在医学数据上继续训练的

dizhenx commented 1 year ago

应该是用finetune_others_continue.sh训练吧

Facico commented 1 year ago

@dizhenx 在额外的数据上是的