Skip to content
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

Problem with Serbian Latin (and I guess Croatian as well) in talk-llama #1736

Open
marko-radojcic opened this issue Jan 8, 2024 · 3 comments
Assignees
Labels
enhancement New feature or request

Comments

@marko-radojcic
Copy link

Hello, I was playing with talk-llama and unlike stream it doesn't recognize these characters, it just omits them.

I've tried adding the unicode page to unicode.h but talk-llama seems to only handle char type not wide characters - or am I wrong ?

@bobqianic bobqianic added the enhancement New feature or request label Jan 9, 2024
@marko-radojcic
Copy link
Author

I just tested a quick and dirty patch to make it work, just commented out the regex filtering on line 506 of talk-lamma.cpp

@marko-radojcic
Copy link
Author

Maybe a command line switch to turn it off or to simply turn it off when language is not English ? Other option is to improve the regex filter maybe...

@bobqianic bobqianic linked a pull request Jan 15, 2024 that will close this issue
11 tasks
@bobqianic bobqianic removed a link to a pull request Feb 2, 2024
11 tasks
@bobqianic bobqianic self-assigned this Feb 2, 2024
@petterreinholdtsen
Copy link
Contributor

This is related to issue #923.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

3 participants