Update Gradio app with multiple files

app.py

@@ -1,7 +1,7 @@
 import spaces
 import gradio as gr
 import torch
-from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
+from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
 from PIL import Image
 import numpy as np
 from typing import List, Dict, Any, Optional, Tuple
@@ -12,9 +12,9 @@ import base64
 model_id = "Qwen/Qwen3-VL-4B-Instruct"  
 
 # Load model with optimizations for inference
-model = Qwen2VLForConditionalGeneration.from_pretrained(
+model = Qwen3VLForConditionalGeneration.from_pretrained(
     model_id,
-    torch_dtype=torch.bfloat16,
+    dtype="auto",
     device_map="auto"
 )
 processor = AutoProcessor.from_pretrained(model_id)
@@ -72,24 +72,14 @@ def process_chat_message(
         })
     
     # Prepare inputs for the model
-    text = processor.apply_chat_template(
+    inputs = processor.apply_chat_template(
         messages,
-        tokenize=False,
-        add_generation_prompt=True
+        tokenize=True,
+        add_generation_prompt=True,
+        return_dict=True,
+        return_tensors="pt"
     )
     
-    if image is not None:
-        inputs = processor(
-            text=[text],
-            images=[image],
-            return_tensors="pt"
-        ).to(model.device)
-    else:
-        inputs = processor(
-            text=[text],
-            return_tensors="pt"
-        ).to(model.device)
-    
     # Generate response
     with torch.no_grad():
         generated_ids = model.generate(