Update custom_st.py

custom_st.py

@@ -53,9 +53,6 @@ class Transformer(nn.Module):
             'max_pixels': max_pixels,
             'cache_dir': cache_dir
         })
-
-        # remove trust_remote_code
-        model_kwargs.pop('trust_remote_code', None)
         
         # Initialize model
         self.model = Qwen2VLForConditionalGeneration.from_pretrained(
@@ -259,7 +256,7 @@ class Transformer(nn.Module):
 
         # ensure inputs are on the same device as the model
         device = next(self.model.parameters()).device
-        inputs = {k: v.to(device) for k, v in inputs.items()}
+        inputs = {k: v.to(device) for k, v in inputs.items() if isinstance(v, torch.Tensor)}
 
         with torch.no_grad():
             output = self.model(
@@ -274,7 +271,7 @@ class Transformer(nn.Module):
         )
         return features
 
-    def tokenize(self, texts: List[Union[str, Image.Image]], padding: str = 'longest') -> Dict[str, torch.Tensor]:
+    def tokenize(self, texts: List[Union[str, Image.Image, bytes]], padding: str = 'longest') -> Dict[str, torch.Tensor]:
         processed_texts, processed_images = self._process_input(texts)
         
         return self.processor(