Xu Tianci

> https://huggingface.co/datasets/JosephusCheung/GuanacoDataset 您好，请问在这个数据集的instruction中会出现Assistant，这是用以多轮对话训练的吗？

> Thanks to your `tokenizer.py`, I prepared my input file successfully. However, when I started training, the following problem appeared: OSError: /usr/local/lib/python3.6/site-packages/flyvec/src/model_descriptor.so: cannot open shared object file: No such file...

> Have you run `bash short_make`? (located inside `flyvec/src`) Thank you for your help. I used another method(`CMake`) instead of `short make`, but your approach is much simpler.

> > 在P40显卡下也是一样的情况，以下是我的实验记录： > > > > * 不启用fp16，load_in_8bit True bs == 2，占用显存18G左右 > > * 不启用fp16，load_in_8bit True bs == 1，占用显存12G左右 > > * 不启用fp16，load_in_8bit False bs == 1，RuntimeError: expected...

启用fp16, load_in_8bit设置为False, 会出现以下报错： RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument mat2 in method...

> 启用fp16, load_in_8bit设置为False, 会出现以下报错： RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument mat2 in...

> 你这个问题跟先有鸡还是先有蛋是一个道理 我知道你的意思，主要是想着要是已经有了（只不过我不知道）好的自动生成的方法，就可以节省大量人工成本了orz