Update app.py

app.py

@@ -50,7 +50,7 @@ def chat(message, history, system_prompt):
     inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
     outputs = model.generate(
         **inputs,
-        max_new_tokens=256,
+        max_new_tokens=1024,
         temperature=0.7,
         do_sample=True,
         pad_token_id=tokenizer.eos_token_id