-
Notifications
You must be signed in to change notification settings - Fork 21
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* Fix ChatGLM Detokenization New special tokens was added to ChatGLM repository, that causes Sentencepiece to crash during decoding because of indices was not added to the main vocabulary (these tokens was not marked as special in the repository and were filtered out because of it). Include tokens to a vocab and also align vocab sizes better. Has to lower pass rate, because of ChatGLM3 decoder inserts spaces between special tokens and Sentencepiece does not. No functional difference between actual texts. * Fix Sentencepiece BOS Token Detection The sentencepiece model cannot add bos_token when there is no bos_token in the dictionary. In such situations `add_eos=True` leads to a failed check inside the sentencepiece library. Modify the `add_bos_token` flag logic to avoid such situations. There is a regression for `camembert-base_slow` tokenizer that is not caused by a bug fix. Had to lower the pass rate to not block the fix. * Add Subfolder Argument to CLI
- Loading branch information
Showing
5 changed files
with
66 additions
and
14 deletions.
There are no files selected for viewing
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
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
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
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,3 +1,3 @@ | ||
{ | ||
"tokenizers_test.py::test_": 0.9201055995553703 | ||
"tokenizers_test.py::test_": 0.8700921600807978 | ||
} |
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