Update app.py

app.py

@@ -57,7 +57,7 @@ def model_inference(input_dict, history):
 
     # Set up streamer for real-time output
     streamer = TextIteratorStreamer(processor, skip_prompt=True, skip_special_tokens=True)
-    generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=1024)
+    generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=2048)
 
     # Start generation in a separate thread
     thread = Thread(target=model.generate, kwargs=generation_kwargs)
@@ -86,7 +86,7 @@ examples = [
 
 demo = gr.ChatInterface(
     fn=model_inference,
-    description="# **Qwen2.5-VL-3B-Instruct**",
+    description="# **Qwen2.5-VL-7B-Instruct**",
     examples=examples,
     textbox=gr.MultimodalTextbox(label="Query Input", file_types=["image"], file_count="multiple"),
     stop_btn="Stop Generation",