update README.md

README.md

@@ -73,7 +73,7 @@ inputs = processor(
 inputs = inputs.to("cuda")
 
 # Inference: Generation of the output
-generated_ids = model.generate(**inputs, max_new_tokens=128)
+generated_ids = model.generate(**inputs, max_new_tokens=128, do_sample=False)
 generated_ids_trimmed = [
     out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
 ]