@ -77,3 +77,5 @@ python example-chat.py ./model ./tokenizer/tokenizer.model
If you wish to stop generation not by "\n" sign, but by another signature, like "User:" (which is also good idea), or any other, make the following modification in the llama/generator.py:

-5 means to remove last 5 chars from resulting context, which is also the lenght of your stop signature, "User:" in this example.