SEC
Software Engineering Courses (SECourses)•4mo ago
Evan

anyone get `RuntimeError: mixed dtype (

anyone get RuntimeError: mixed dtype (CPU): expect parameter to have scalar type of Float when following the full flux finetune tutorial?
1 Reply
Evan
EvanOP•4mo ago
called from: 
File "/teamspace/studios/this_studio/kohya_ss/sd-scripts/library/strategy_flux.py", line 68, in encode_tokens
    l_pooled = clip_l(l_tokens.to(clip_l.device))["pooler_output"]
-----
"/home/zeus/miniconda3/envs/cloudspace/lib/python3.10/site-packages/torch/nn/modules/normalization.py", line 217, in forward
    return F.layer_norm(
  File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.10/site-packages/torch/nn/functional.py", line 2900, in layer_norm
    return torch.layer_norm(
RuntimeError: mixed dtype (CPU): expect parameter to have scalar type of Float
File "/teamspace/studios/this_studio/kohya_ss/sd-scripts/library/strategy_flux.py", line 68, in encode_tokens
    l_pooled = clip_l(l_tokens.to(clip_l.device))["pooler_output"]
-----
"/home/zeus/miniconda3/envs/cloudspace/lib/python3.10/site-packages/torch/nn/modules/normalization.py", line 217, in forward
    return F.layer_norm(
  File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.10/site-packages/torch/nn/functional.py", line 2900, in layer_norm
    return torch.layer_norm(
RuntimeError: mixed dtype (CPU): expect parameter to have scalar type of Float
i was running lighting.ai on CPU mode by accident 🤦

Did you find this page helpful?