-
Notifications
You must be signed in to change notification settings - Fork 1.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Address the feedback on the tokenizer's library #7024
Merged
Merged
Changes from 5 commits
Commits
Show all changes
23 commits
Select commit
Hold shift + click to select a range
f6e32f5
Fix cache when calling EncodeToIds
tarekgh 0553922
Make EnglishRoberta _mergeRanks thread safe
tarekgh a4cb1f5
Delete Trainer
tarekgh 6a13025
Remove the setters on the Bpe properties
tarekgh 3278aff
Remove Roberta and Tiktoken special casing in the Tokenizer and suppo…
tarekgh b5f7fa2
Support text-embedding-3-small/large embedding
tarekgh a11f4e0
Remove redundant TokenToId abstraction and keep the one with the extr…
tarekgh 865068a
Enable creating Tiktoken asynchronously or directly using the tokeniz…
tarekgh 4077de0
Add cancellationToken support in CreateAsync APIs
tarekgh 5aaf849
Rename sequence to text and Tokenize to Encode
tarekgh b5e0927
Rename skipSpecialTokens to considerSpecialTokens
tarekgh 5e26b3e
Rename TokenizerResult to EncodingResult
tarekgh 985de8a
Make Token publicly immutable
tarekgh b551e7d
Change offset tuples from (Index, End) to (Index, Length)
tarekgh 7ea7f70
Rename NormalizedString method's parameters
tarekgh b0c8244
Rename Model's methods to start with verb
tarekgh 450418a
Convert Model.GetVocab() method to a Vocab property
tarekgh 6f53de8
Some method's parameters and variable renaming
tarekgh 62334c6
Remove Vocab and VocabSize from the abstraction
tarekgh d48b32d
Cleanup normalization support
tarekgh 191ab03
Minor Bpe cleanup
tarekgh b9b0f58
Resolve rebase change
tarekgh 1ad157f
Address the feedback
tarekgh File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'm having trouble understanding what this means.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
If encoding text with Bpe model, for the tokens that the model doesn't recognize, it uses the unknown token for it. Most users uses
[Unk]
for the unknow token. It is possible to get multiple[Unk]
tokens next to each others in the result. SettingsfuseUnknownTokens
to true cause all[Unk]
sequence to collapse into one[Ukn]
. Fuse term is used by Huggingface and users of Bpe are familiar with that. If you have better explanation we can use here I'll be happy to use it :-)