Update app.py

app.py

@@ -21,5 +21,5 @@ messages = [
 ]
 
 inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
-outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+outputs = model.generate(inputs, max_new_tokens=512, do_sample=True, top_k=50, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
 res = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)