Smartness increased to max_new_tokens=50

app.py

@@ -173,7 +173,7 @@ async def process_prompt(request: PromptRequest):
         with torch.no_grad():
             outputs = model.generate(
                 **inputs,
-                max_new_tokens=100,
+                max_new_tokens=50,
                 do_sample=True,
                 top_p=0.95,
                 temperature=0.8,