Implement non-greedy tokenizer that tries to maximize token lengths#242
Merged
Conversation
Contributor
|
Although I haven't examined the code, I've tested it on several prompts and can already conclude that this patch allows Llama to write in French. |
j-f1
reviewed
Mar 17, 2023
Piezoid
reviewed
Mar 17, 2023
Contributor
There was a problem hiding this comment.
Is the space meant to be a separate token? I noticed that it often get fused with the first user provided token.
Contributor
Author
There was a problem hiding this comment.
It should be fused to the first token! This is how original python llama code parses it.
I can dig out more details if you want.
ggerganov
approved these changes
Mar 17, 2023
ggerganov
left a comment
Member
There was a problem hiding this comment.
Merge it if results look ok.
I won't be able to have detailed look in the next few days
- this is to match original llama tokenizer behavior
mudler
pushed a commit
to go-skynet/llama
that referenced
this pull request
Mar 17, 2023
…gml-org#242) * Implement non-greedy tokenizer that tries to maximize token lengths * Insert single space in front of the prompt - this is to match original llama tokenizer behavior --------- Co-authored-by: Jakub Horak <jakub.horak@ibawizard.net>
antimatter15
pushed a commit
to antimatter15/alpaca.cpp
that referenced
this pull request
Mar 18, 2023
…gml-org#242) * Implement non-greedy tokenizer that tries to maximize token lengths * Insert single space in front of the prompt - this is to match original llama tokenizer behavior --------- Co-authored-by: Jakub Horak <jakub.horak@ibawizard.net>
gyohng
pushed a commit
to gyohng/alpaca.cpp
that referenced
this pull request
Mar 26, 2023
…gml-org#242) * Implement non-greedy tokenizer that tries to maximize token lengths * Insert single space in front of the prompt - this is to match original llama tokenizer behavior --------- Co-authored-by: Jakub Horak <jakub.horak@ibawizard.net>
Seunghhon
pushed a commit
to Seunghhon/llama.cpp
that referenced
this pull request
Apr 26, 2026
…gml-org#242) * Implement non-greedy tokenizer that tries to maximize token lengths * Insert single space in front of the prompt - this is to match original llama tokenizer behavior --------- Co-authored-by: Jakub Horak <jakub.horak@ibawizard.net>
ljubomirj
pushed a commit
to ljubomirj/llama.cpp
that referenced
this pull request
May 6, 2026
…gml-org#242) * Implement non-greedy tokenizer that tries to maximize token lengths * Insert single space in front of the prompt - this is to match original llama tokenizer behavior --------- Co-authored-by: Jakub Horak <jakub.horak@ibawizard.net>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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.
No description provided.