Use do_sample=False for greedy decoding

app.py

@@ -14,7 +14,7 @@ def generate_response(prompt):
     """
     chat = [{"role": "user", "content": prompt}]
     inputs = tokenizer.apply_chat_template(chat, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
-    outputs = model.generate(inputs, max_new_tokens=512, temperature=0.0)
+    outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)
     
     # Decode the generated text
     generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
@@ -42,4 +42,4 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()