billchen
RRunPod
•Created by billchen on 3/30/2024 in #⚡｜serverless
copying a param with shape torch.Size([2048, 1280]) from checkpoint, the shape in current model is t
I was using the https://github.com/ashleykleynhans/runpod-worker-instantid project, and then I changed the original model wangqixun/YamerMIX_v8 to Justin-Choo/XXMix_9realisticSDXL. Then an error occurred.
show error：
"Error(s) in loading state_dict for Resampler:\n\tsize mismatch for proj_out.weight: copying a param with shape torch.Size([2048, 1280]) from checkpoint, the shape in current model is torch.Size([768, 1280]).\n\tsize mismatch for proj_out.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([768]).\n\tsize mismatch for norm_out.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([768]).\n\tsize mismatch for norm_out.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([768])."
6 replies