Use CLIP model config to set some kwargs for components (#16609)

* Use CLIP model's config for some fields (if specified) instead of those of vision & text components.
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

src/transformers/models/clip/modeling_clip.py

@@ -898,6 +898,13 @@ class CLIPModel(CLIPPreTrainedModel):
         >>> inputs = tokenizer(["a photo of a cat", "a photo of a dog"], padding=True, return_tensors="pt")
         >>> text_features = model.get_text_features(**inputs)
         ```"""
+        # Use CLIP model's config for some fields (if specified) instead of those of vision & text components.
+        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
+        output_hidden_states = (
+            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        )
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
         text_outputs = self.text_model(
             input_ids=input_ids,
             attention_mask=attention_mask,
@@ -942,6 +949,13 @@ class CLIPModel(CLIPPreTrainedModel):
 
         >>> image_features = model.get_image_features(**inputs)
         ```"""
+        # Use CLIP model's config for some fields (if specified) instead of those of vision & text components.
+        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
+        output_hidden_states = (
+            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        )
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
         vision_outputs = self.vision_model(
             pixel_values=pixel_values,
             output_attentions=output_attentions,
@@ -991,7 +1005,13 @@ class CLIPModel(CLIPPreTrainedModel):
         >>> logits_per_image = outputs.logits_per_image  # this is the image-text similarity score
         >>> probs = logits_per_image.softmax(dim=1)  # we can take the softmax to get the label probabilities
         ```"""
-        return_dict = return_dict if return_dict is not None else self.config.return_dict
+        # Use CLIP model's config for some fields (if specified) instead of those of vision & text components.
+        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
+        output_hidden_states = (
+            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        )
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
         vision_outputs = self.vision_model(
             pixel_values=pixel_values,
             output_attentions=output_attentions,