huyoa

> Here are some steps to resolve this issue: > > 1. Check if DeepSpeed is installed: Run `pip list` or `pip freeze` in your terminal to see if DeepSpeed...

I also encountered the same problem

> vicuna使用本地模型启动，单卡没问题，双卡就出现 ValueError: The device_map provided does not give any device for the following parameters: model.embed_tokens.weight, model.layers.0.self_attn.q_proj.weight, > > > 启动时如果判断torch.cuda.is_available返回为Ture且有多卡会自动把模型分配在多卡中运行 @elven2016 请问这个问题解决了吗