Generate: Export TF generate with a TF tokenizer #22310
Merged
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
|
@Rocketknight1 no need to review, but FYI -- we can now compile the whole thing into a graph :D |
4 tasks
amyeroberts
reviewed
Mar 22, 2023
amyeroberts
approved these changes
Mar 22, 2023
|
The documentation is not available anymore as the PR was closed or merged. |
gante
force-pushed
the
export_tf_generate_with_tokenizer
branch
from
96914db to
db3f426
Compare
|
This is amazing! |
raghavanone
pushed a commit
to raghavanone/transformers
that referenced
this pull request
Apr 5, 2023
* Export TF generate with a TF tokenizer * remove unused lines
novice03
pushed a commit
to novice03/transformers
that referenced
this pull request
Jun 23, 2023
* Export TF generate with a TF tokenizer * remove unused lines
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Outdated suggestions cannot be applied.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.
What does this PR do?
See #22254
As the title says, this PR adds the possibility to export TF generate with a TF-native tokenizer -- the full thing in a single TF graph 🤯
The missing piece was removing a redundant
ifbeforetf.while_cond--tf.while_condchecks the condition before running the body, so the existingifbefore it was redundant. It was also the root cause behind the error in #22254, so removing it was a double win 🎉A test was added to ensure we don't regress.