fal

/

moondream2-docci-instruct

like 8

RuntimeError: 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, 1152]) from checkpoint, the shape in current model is torch.Size([8192, 2304]).
You may consider adding ignore_mismatched_sizes=True in the model from_pretrained method.