Update backend/main.py

backend/main.py

@@ -373,7 +373,7 @@ print(f"🔥 Using device: {'GPU' if device==0 else 'CPU'}")
 llm_pipeline = pipeline(
     "text-generation",
     model="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
-    max_new_tokens=1024,
+    max_new_tokens=512,
     temperature=0.7,
     device=device
 )