rror occurred when executing T5TextEncoderLoader #ELLA: Error(s) in loading state_dict for T5EncoderModel: size mismatch for shared.weight: copying a param with shape torch.Size([32128, 2048]) from checkpoint, the shape in current model is torch.Size([32128, 512]). size mismatch for encoder.block.0.layer.0.SelfAttention.q.weight: copying a param with shape torch.Size([2048, 2048]) from checkpoint, the shape in current model is torch.Size([512, 512]).

TencentQQGYLab / ComfyUI-ELLA

ELLA nodes for ComfyUI

347 stars 18 forks source link

rror occurred when executing T5TextEncoderLoader #ELLA: Error(s) in loading state_dict for T5EncoderModel: size mismatch for shared.weight: copying a param with shape torch.Size([32128, 2048]) from checkpoint, the shape in current model is torch.Size([32128, 512]). size mismatch for encoder.block.0.layer.0.SelfAttention.q.weight: copying a param with shape torch.Size([2048, 2048]) from checkpoint, the shape in current model is torch.Size([512, 512]). #48

Closed flyricci closed 6 months ago

flyricci commented 6 months ago

rror occurred when executing T5TextEncoderLoader #ELLA:

Error(s) in loading state_dict for T5EncoderModel: size mismatch for shared.weight: copying a param with shape torch.Size([32128, 2048]) from checkpoint, the shape in current model is torch.Size([32128, 512]). size mismatch for encoder.block.0.layer.0.SelfAttention.q.weight: copying a param with shape torch.Size([2048, 2048]) from checkpoint, the shape in current model is torch.Size([512, 512]).

Skuuurt commented 4 months ago

I have the same problem, please can you tell how to solve this ?