Error(s) in loading state_dict for Moondream:
size mismatch for vision_encoder.projection.mlp.fc1.weight: copying a param with shape torch.Size([8192, 2304]) from checkpoint, the shape in current model is torch.Size([8192, 1152]).
You may consider adding ignore_mismatched_sizes=True in the model from_pretrained method.
Moondream2 has this issue, while moondream1 is fine.
Error occurred when executing MoondreamQuery:
Error(s) in loading state_dict for Moondream: size mismatch for vision_encoder.projection.mlp.fc1.weight: copying a param with shape torch.Size([8192, 2304]) from checkpoint, the shape in current model is torch.Size([8192, 1152]). You may consider adding
ignore_mismatched_sizes=True
in the modelfrom_pretrained
method.Moondream2 has this issue, while moondream1 is fine.
What is broken?