fix: add explicit temperature and top_p parameters to avoid warnings.

app.py

@@ -128,6 +128,8 @@ def generate_response_gpu(prompt, max_tokens=512):
                 **inputs,
                 max_new_tokens=max_tokens,
                 do_sample=False,
+                temperature=None,
+                top_p=None,
                 pad_token_id=tokenizer.pad_token_id,
                 eos_token_id=tokenizer.eos_token_id,
                 repetition_penalty=1.1,