Open ilqin opened 1 month ago
Library version incompatibility: the version of transformers or torch may not be fully compatible with the code. Model loading problem: the model file may be corrupted or incomplete. Memory problem: This may be caused by insufficient video memory.
Library version incompatibility: the version of transformers or torch may not be fully compatible with the code. Model loading problem: the model file may be corrupted or incomplete. Memory problem: This may be caused by insufficient video memory.
Could you please list a working library version of torch, transformers, torchvision? I'm running on 4090 with 60gb mem torch 2.1.2. and got the issue
Library version incompatibility: the version of transformers or torch may not be fully compatible with the code. Model loading problem: the model file may be corrupted or incomplete. Memory problem: This may be caused by insufficient video memory.
Could you please list a working library version of torch, transformers, torchvision? I'm running on 4090 with 60gb mem torch 2.1.2. and got the issue
transformers >= 4.45.0 torchvision >= 0.17 accelerate >= 0.26.0 numpy >= 1.24.4
Library version incompatibility: the version of transformers or torch may not be fully compatible with the code. Model loading problem: the model file may be corrupted or incomplete. Memory problem: This may be caused by insufficient video memory.
Could you please list a working library version of torch, transformers, torchvision? I'm running on 4090 with 60gb mem torch 2.1.2. and got the issue
transformers >= 4.45.0 torchvision >= 0.17 accelerate >= 0.26.0 numpy >= 1.24.4
I upgrade to torch 2.4.1 and it solves
我也是楼主的这个问题
Molmo7BDbnb all() received an invalid combination of arguments - got (Tensor, dim=tuple, keepdim=bool), but expected one of: (Tensor input, , Tensor out) didn't match because some of the keywords were incorrect: dim, keepdim (Tensor input, int dim, bool keepdim, , Tensor out) (Tensor input, name dim, bool keepdim, , Tensor out)
ComfyUI Error Report
Error Details
Stack Trace
`
Additional Context
(Please add any additional context or steps to reproduce the error here)