Repo for BenTsao [original name: HuaTuo (华驼)], Instruction-tuning Large Language Models with Chinese Medical Knowledge. 本草(原名:华驼)模型仓库,基于中文医学知识的大语言模型指令微调
I tried to train the model in RTX3090(24G) with batch_size=32 and got the problem "CUDA out of memory," even though I set the batch_size=8, I got the same problem.
The detail logs are Here.
I look forward to your advice.
I tried to train the model in RTX3090(24G) with batch_size=32 and got the problem "CUDA out of memory," even though I set the batch_size=8, I got the same problem. The detail logs are Here. I look forward to your advice.