Whenever I try to run the training (using default settings), I am getting the following error when executing ADMD_TrainLora node:
RuntimeError: Expected tensor for argument #1 'indices' to have one of the following scalar types: Long, Int; but got torch.cuda.FloatTensor instead (while checking arguments for embedding)
I am running ComfyUI on 4090RTX with Cuda 12.1 and torch version 2.1.2. Any idea what might be causing it?
Whenever I try to run the training (using default settings), I am getting the following error when executing ADMD_TrainLora node:
RuntimeError: Expected tensor for argument #1 'indices' to have one of the following scalar types: Long, Int; but got torch.cuda.FloatTensor instead (while checking arguments for embedding)I am running ComfyUI on 4090RTX with Cuda 12.1 and torch version 2.1.2. Any idea what might be causing it?