Update README.md

README.md

@@ -48,7 +48,10 @@ generator = pipeline(
     model_kwargs={"torch_dtype": torch.bfloat16},
     device="cuda",
 )
-outputs = generator([{"role": "user", "content": "What's the difference between llamas and alpacas?"}], do_sample=False, max_new_tokens=200)
+outputs = generator([{"role": "user", "content": "What's the difference between llamas and alpacas?"}],
+                      do_sample=False,
+                      eos_token_id=[generator.tokenizer.convert_tokens_to_ids("<end_of_turn>"), generator.tokenizer.eos_token_id],
+                      max_new_tokens=200)
 print(outputs[0]['generated_text'])
 ```