Upload folder using huggingface_hub

modeling_pantagruel_uni.py

@@ -1555,6 +1555,7 @@ class PantagruelUniModel(PantagruelUniPreTrainedModel):
         self,
         input_values=None, # audio input
         input_ids=None, # text input
+        token_type_ids=None,
         attention_mask=None,
         padding_mask=None,
         mask=False,
@@ -1623,7 +1624,7 @@ class PantagruelUniModel(PantagruelUniPreTrainedModel):
             mode = "TEXT" if input_ids is not None else "AUDIO"
 
         if padding_mask is None and attention_mask is not None:
-            padding_mask = ~attention_mask # attention mask: 1 means to attend to (not masked), 0 means not to attend to (masked). padding mask: 1 means padded (not attend to), 0 means not padded (to attend to)
+            padding_mask = ~attention_mask.bool() # attention mask: 1 means to attend to (not masked), 0 means not to attend to (masked). padding mask: 1 means padded (not attend to), 0 means not padded (to attend to)
 
         feature_extractor = self.modality_encoders[mode]
         extractor_out = feature_extractor(