logging added and max new token size reduced

app.py

@@ -26,13 +26,20 @@ def analyze_palm(image, question, history):
 
     # Add <image> token explicitly in the text
     prompt = f"<image>\n{question}"
+    print("Processing image and prompt")
+
     # Manual prompt construction (works for TinyLLaVA)
     inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
+    print("Inputs encoded")
+
+    outputs = model.generate(**inputs, max_new_tokens=256)
+    print("Output generated")
 
-    outputs = model.generate(**inputs, max_new_tokens=512)
     response = processor.decode(outputs[0], skip_special_tokens=True)
 
     history.append((question, response))
+    print("Returning response")
+
     return history, ""