llama : remove notion of CLS token #11064
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
danbev
approved these changes
Jan 5, 2025
Member
danbev
left a comment
danbev
left a comment
There was a problem hiding this comment.
So this is only about the CLS token itself, which is not used in decoders hence only the BOS is needed, and has nothing to do with the pooling type CLS right?
Member
Author
Yes, this is not related to the pooling types. We haven't used the CLS token in any of the examples yet, so I think this is a safe change. |
ggerganov
force-pushed
the
gg/llama-refactor-5
branch
2 times, most recently
from
747c85d to
2772050
Compare
ggerganov
force-pushed
the
gg/llama-refactor-5
branch
from
2772050 to
00f2b4c
Compare
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Feb 26, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
target #11062
My understanding is that there is no need to distinguish between BOS and CLS tokens, so we can simplify the implementation logic by removing CLS.