-
Notifications
You must be signed in to change notification settings - Fork 538
Conversation
Codecov Report
@@ Coverage Diff @@
## master #866 +/- ##
===========================================
+ Coverage 73.87% 89.74% +15.86%
===========================================
Files 67 67
Lines 6423 6423
===========================================
+ Hits 4745 5764 +1019
+ Misses 1678 659 -1019
|
Job PR-866/1 is complete. |
Job PR-866/2 is complete. |
Job PR-866/4 is complete. |
Job PR-866/5 is complete. |
Is this ready? |
This only contains the model and no fine-tuning scripts. For finetuning, designing a joint API encompasses the existing bert scripts and works for XLNet and moving that to the main package would be a way forward. That can be done in a separate PR though I guess. |
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 don't see an example usage of XLNet with tokenizers and how I can get it with xx.get_model API. Are you going to add it?
@leezu pinging for an update |
@leezu @eric-haibin-lin gentle ping |
@eric-haibin-lin an example is included now https://github.com/dmlc/gluon-nlp/pull/866/files#diff-820020a4c66a085eb27014cc377a8658 |
Job PR-866/7 is complete. |
Job PR-866/8 is complete. |
Job PR-866/9 is complete. |
Job PR-866/10 is complete. |
Job PR-866/11 is complete. |
Currently unused, but included for future-compatibility of parameter files
We can't create a sentencepiece model from the vocabulary alone. As long as GluonNLP does not reimplement sentencepiece tokenization, the binary model needs to distributed as well.
Job PR-866/12 is complete. |
Avoid concurrency failure in gluon's get_model_file
Job PR-866/13 is complete. |
Job PR-866/15 is complete. |
CI passes now |
Description
Add XLNet conversion scripts
Checklist
Essentials
Changes
Comments
This PR resolves #787