Skip to content

Added option to prevent tokens from being penalized for repetition #426

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

Closed
wants to merge 1 commit into from

Conversation

Lyrcaxis
Copy link
Contributor

@Lyrcaxis Lyrcaxis commented Apr 24, 2024

Idea is to allow excluding common tokens like * " , . ! ? my your, or even <eos> from being penalized for repetition.
This is because in creative writing they may need to appear quite often, and without this, the syntax can get all over the place.

Currently accepts a list[int] meaning the sended should already have tokenized their text.
Alternatively could accept a list[string] and tokenize on the fly, if there are no performance concerns.

@Qubitium
Copy link

@Lyrcaxis I like the idea but instead of excluding them from penality, it would be more powerful to apply a different penalty to them. You still don't want ! to be repeated 100 times for example.

@p-e-w
Copy link
Contributor

p-e-w commented May 12, 2024

See this PR for a mechanism that attempts to solve the same problem automatically, without needing to maintain a list of excluded tokens.

@Lyrcaxis Lyrcaxis closed this May 22, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants