Add GPT2 tokenizer setup and refactor code #56
Merged
+485
−398
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
aliciafmachado
force-pushed
the
gpt-tokenizer
branch
from
3d0d0c6 to
050e136
Compare
iislucas
reviewed
Jan 28, 2025
| embedBatch, | ||
| expectedOutputSeqPrepFn, | ||
| } from '../tokens/token_gemb'; | ||
|
|
||
| function tokenize_fn_test(input: string): number[] { |
There was a problem hiding this comment.
I'm not sure I get what this function is for, can you add a comment to say a little about what it's intended to do.
There was a problem hiding this comment.
It's a function for testing. Added a comment and simplified it.
…ing the local task token rep. There seems to be a memory leak, and a refactoring is necessary.
…ngle file. Refactor token gemb file so that embedBatch is adapted to a use case where a tokenizer is available.
…le with next N tokens prediction.
aliciafmachado
force-pushed
the
gpt-tokenizer
branch
from
999531a to
b2fbcc9
Compare
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Outdated suggestions cannot be applied.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.
Main changes introduced are:
gpt-tokenizerlibrary.token_gemb.tsfile to make it simpler to extend it to other tokenizations.gpt2.tsandtransformer_gtensor.tsto a common file.Fixes Issues #54 & #52.
Refactoring the token embedding type and wrapping it with a class will be done in a follow-up CL.
There is also some work left on refactoring the tokenization of tasks so that we can reuse the tokens for next N tokens prediction.