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Outdated suggestions cannot be applied.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.
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
Adding needed Tokenizer's APIs #7047
Adding needed Tokenizer's APIs #7047
Changes from 5 commits
ca18ba7
4832f9a
d9c1524
5041ebf
765f79a
b9e95b2
1d89506
File filter
Filter by extension
Conversations
Jump to
There are no files selected for viewing
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.
EncodeToIds takes a span but Encode takes a string. Is that ok? Are there places it'd be valuable for Encode to also take a span, or are there benefits to it being a string?
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.
IIRC we chatted about that before. Encode need to return tokens, if we pass ReadOnlySpan here we'll need to call ToString on it again. EncodeToIds doesn't need return tokens and that is why we are ok to use spans there. I am open to any suggestion if we have a better ideas.
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.
Hmm. Is that because we expect this text to frequently be a single token?
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.
Tokenizers using Regex to pre-tokenize and produces a smaller or partial words is possible to be a single token. So it depends on the pre-tokenization and the vocabulary of the tokenizer. You had another idea which we decided not go with but we can reconsider it which is passing both string and span. This can help in the future if we expose Span apis on Tokenizer class.
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 could imagine someone wanting an API like
IEnumerable<byte> Decode(IEnumerable<ids> ids, ...)
. Presumably if that was desired we could always add it in the future.