Jaihyun Lew
Jaihyun Lew
Thank you for the explanation. Some additional questions: 1. Then are the results reported in the paper experimented in the form of FC->Norm->Relu->Norm->FC->Relu ? 2. I get that Normalization needs...
you may need to install the `gdown` command by `pip install gdown`.
Same question here, I failed to understand that part. In addition, I am having a little struggle in reading, and wish for a detailed description of your wonderful work for...
in my case, I had to match all versions of `nvcc --version` and `torch.version.cuda` to the one right for mamba-ssm, which is in your case, **12.4**. Try changing them all...