antoinelouis

/

splade-max-camembert-base-mmarcoFR

like 0

Hi! Very excited to try the ONLY sparse vector in French I could find.

I'm getting the following error when trying the code on the model card:

File "/Users/osuz/Library/Application Support/JetBrains/PyCharm2023.3/scratches/scratch.py", line 18, in
q_activations = torch.amax(torch.log1p(relu(q_output.logits * q_input['attention_mask'].unsqueeze(-1))), dim=1)
^^^^^^^^^^^^^^^
AttributeError: 'BaseModelOutputWithPoolingAndCrossAttentions' object has no attribute 'logits'

Any ideas?

Thanks in advance!