Skip to content

Conversation

@ngxson
Copy link
Collaborator

@ngxson ngxson commented Mar 14, 2024

@phymbert phymbert removed their assignment Mar 14, 2024
@ngxson ngxson requested a review from ggerganov March 14, 2024 21:57
@phymbert
Copy link
Collaborator

@ngxson you assigned me something ? I have no value added at the moment on chat templates. But your contribution to support new ones taking into account our plain old c++ is very useful.
If I can help by adding some tests, ping me.

@ngxson
Copy link
Collaborator Author

ngxson commented Mar 14, 2024

@phymbert sorry I misclicked and didn’t notice that. Don’t worry though. And to response to your deleted message: Et oui je parle français ;-)

@ngxson
Copy link
Collaborator Author

ngxson commented Mar 14, 2024

Btw this template is so weird, they have EOS token everywhere. Looks like some researchers “just do it” and don’t care about optimizing

@ggerganov ggerganov merged commit aab606a into ggml-org:master Mar 15, 2024
hodlen pushed a commit to hodlen/llama.cpp that referenced this pull request Apr 3, 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.

Orion-14B chat template is not support

3 participants