Update README.md

README.md

@@ -69,7 +69,7 @@ messages = [
  ]
 tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
 
-outputs = model.generate(tokenized_chat, max_new_tokens=128) 
+outputs = model.generate(tokenized_chat, stop_strings=["<extra_id_1>"], tokenizer=tokenizer)
 print(tokenizer.decode(outputs[0]))
 ```
 
@@ -85,7 +85,7 @@ messages = [
     {"role": "user", "content": "Who are you?"},
 ]
 pipe = pipeline("text-generation", model="nvidia/Mistral-NeMo-Minitron-8B-Instruct")
-pipe(messages, max_length=64)
+pipe(messages, max_new_tokens=64, stop_strings=["<extra_id_1>"], tokenizer=tokenizer)
 ```
 
 ## Evaluation Results