Update app.py

app.py

@@ -257,11 +257,11 @@ app.add_middleware(
 )
 
 generation_config = GenerationConfig(
-    max_new_tokens=150,
-    temperature=0.7,
-    top_k=20,
+    max_new_tokens=200,
+    temperature=0.3,
+    top_k=50,
     do_sample=True,
-    top_p=0.8,
+    top_p=0.9,
 )
 
 # Create generation pipeline
@@ -334,7 +334,11 @@ async def chat_fn(query: Query):
     # Run blocking inference in thread
     loop = asyncio.get_event_loop()
     response = await loop.run_in_executor(executor,
-                                          lambda: pipe(prompt, max_new_tokens=150, temperature=0.7, do_sample=True, top_p=0.9)[0]['generated_text'])
+                                          lambda: pipe(prompt, max_new_tokens=200,
+                                                       temperature=0.3,
+                                                       top_k=50,
+                                                       do_sample=True,
+                                                       top_p=0.9)[0]['generated_text'])
 
     # Parse answer
     answer = response.split("Answer:")[-1].strip() if "Answer:" in response else response.split("الإجابة:")[-1].strip()