Add a way to count tokens without encoding the whole text; improve performance; fix bugs #38
Conversation
This file contains 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
- adds highly performant `isWithinTokenLimit` to count tokens without encoding the whole text - improve overall performance by removing transitive arrays - include precomputed `bpeRanks` - add type-checking - fix a few minor bugs (thanks to type-checking) - add generator versions of both decoder and encoder
niieani
changed the title
niieani
force-pushed
the
bb/count-tokens
branch
from
d32f3e8 to
9d800de
Compare
requires providing an additional argument with cache if you want to make it shared fixes #35
This was referenced Apr 16, 2023
Open
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Outdated suggestions cannot be applied.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.
isWithinTokenLimitto count tokens without encoding the whole textbpeRanksTo test, see fork published as
gpt-tokenizer.