-
Notifications
You must be signed in to change notification settings - Fork 99
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
"+++" continuous writing exception #85
Comments
usually it means the model has decided you have reached [endoftext] |
Most implementations with this model of encoding, decoding, and reverse prompt (myself included) are incorrect. Implementations of encoding will become almost correct with World's greedy tokenizer, but decoding and reverse prompt will still be buggy. I hope to document how to do this properly in the future |
Hm, why, given that official |
implementers forget that sometimes |
Haha, da Lao. I think you are right. |
The novel model "+++" is not output after several times of writing, and other instructions are not output. I can only reset the model.
decoded: str = tokenizer.decode(accumulated_tokens)
if '\uFFFD' not in decoded:
The text was updated successfully, but these errors were encountered: