llama : the WPM vocabs use the CLS token as BOS #10930
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
tinglou
pushed a commit
to tinglou/llama.cpp
that referenced
this pull request
Feb 13, 2025
* llama : the WPM vocabs use the CLS token as BOS ggml-ci * llama : add comment
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Feb 26, 2025
* llama : the WPM vocabs use the CLS token as BOS ggml-ci * llama : add comment
mglambda
pushed a commit
to mglambda/llama.cpp
that referenced
this pull request
Mar 8, 2025
* llama : the WPM vocabs use the CLS token as BOS ggml-ci * llama : add comment
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
https://github.com/ggerganov/llama.cpp/blob/9d5c7115879fe33828edf3a1892b597b61c1cd7d/src/llama-vocab.cpp#L1529-L1535
Not sure if this separation of BOS and CLS tokens is really necessary. The alternative would be to remove the notion of CLS tokens from the codebase and work only with BOS tokens - seems much simpler. The problem would be if there are models that have both BOS and CLS tokens that are distinct?