Support loading tokenizer from local folder #76 #81
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
pcuenca
reviewed
Mar 24, 2024
Sources/Hub/HubApi.swift
Outdated
Comment on lines
100
to
101
| /// Assumes the file has already present at local url. | ||
| /// `url` is complete local file path for given model |
There was a problem hiding this comment.
Suggested change
| /// Assumes the file has already present at local url. | |
| /// `url` is complete local file path for given model | |
| /// Assumes the file is already present at local url. | |
| /// `url` is a complete local file path for the given model |
Sources/Hub/HubApi.swift
Outdated
|
|
||
| /// Assumes the file has already present at local url. | ||
| /// `url` is complete local file path for given model | ||
| func configuration(url: URL) throws -> Config { |
There was a problem hiding this comment.
Maybe call the parameter fileURL to make it clear?
vinu-vanjari
force-pushed
the
support-loading-tokenizer-from-local-folder
branch
from
08d4b56 to
800353c
Compare
pcuenca
approved these changes
Mar 25, 2024
|
Something's up with the CI, but the tests pass locally so I'll merge. Thanks a lot @vinu-vanjari! |
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Outdated suggestions cannot be applied.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.
Resolves #76
Added new method in
AutoTokenizerto load from local model folder.Also added supporting unit tests at
Tests/TokenizersTests/FactoryTests.swiftAlthough we could have simply loaded
tokenizer_config.jsonandtokenizer.jsonfiles directly into configurations, I chose to go viaLanguageModelConfigurationFromHubbecause it has it's own magic for choosing appropriate tokenizer class and it also selects fallback tokenizer if needed refer getter var tokenizerConfig: Config?