Update app.py

app.py

@@ -32,8 +32,8 @@ text_input = "How did Tesla perform in Q1 2024?"
 # Tokenize the input text
 inputs = tokenizer(text_input, return_tensors="pt").to(device)
 
-# Generate a response
-outputs = model.generate(**inputs, max_length=150, temperature=0.7, top_p=0.9, top_k=50)
+# Generate a response without sampling (deterministic)
+outputs = model.generate(**inputs, max_length=150, do_sample=False)
 
 # Decode the generated tokens to a readable string
 response = tokenizer.decode(outputs[0], skip_special_tokens=True)