Fix: The conversion script for English BERT to Fast Tokenizer was incorrect, so tokenization was not performed correctly

Browse Source

...

This commit is contained in:

tsukumi

2024-12-19 11:10:33 +09:00

parent c1fce3fec7

commit 2833fb5eeb

6 changed files with 1024100 additions and 256046 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

640053

bert/deberta-v3-large-onnx/tokenizer.json

File diff suppressed because one or more lines are too long