transformers
Add Whole Word Masking and Padding Strategy to DataCollatorForLanguageModeling
#39485
Merged

Add Whole Word Masking and Padding Strategy to DataCollatorForLanguageModeling #39485

rjgleaton
Rocketknight1
Rocketknight1 commented on 2025-07-18
rjgleaton rjgleaton force pushed from 20b31655 to f1dd7528 135 days ago
rjgleaton
rjgleaton rjgleaton force pushed from f1dd7528 to 8a959377 135 days ago
rjgleaton rjgleaton requested a review from Rocketknight1 Rocketknight1 135 days ago
rjgleaton
Rocketknight1
Rocketknight1 approved these changes on 2025-08-22
rjgleaton rjgleaton requested a review from Rocketknight1 Rocketknight1 100 days ago
Rocketknight1
Rocketknight1
rjgleaton rjgleaton force pushed from 1505215d to e090bf75 94 days ago
rjgleaton
rjgleaton rjgleaton force pushed from e090bf75 to f34f8bd5 93 days ago
Rocketknight1 Rocketknight1 force pushed from f34f8bd5 to 49a2cc0b 90 days ago
Rocketknight1
Rocketknight1 approved these changes on 2025-09-22
rjgleaton Add whole word masking
67ce8830
rjgleaton Vectorize whole word masking functions
21acc1bc
rjgleaton Unit test whole word masking
0a4bd821
rjgleaton Remove support for TF in whole word masking
ee360bf5
Rocketknight1 Rocketknight1 force pushed from 49a2cc0b to ee360bf5 90 days ago
HuggingFaceDocBuilderDev
Rocketknight1 Rocketknight1 merged 2b8a7e82 into main 90 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone