Fix PaliGemma Pad Token Masking During Training #35855 #35859
change order of unmasking of tokens
6a963f3d
library import
a4a5df17
class setup
0122d98a
test function
a7024fe9
refactor
a644110e
add commit message
95443449
test modified
2798e3bb
explict initiliasation of weights + made model smaller
96e1b43f
removed sepete testing file
d0451758
fixup
828a3fef
fixup core
543b7174
test attention mask with token types
1039978a
tests fixup
9a451e2f
Merge branch 'main' into Paliegemma-Token-Mask
64a2a360
removed PaliGemmaAttentionMaskTest class
a015a90b
Merge branch 'main' into Paliegemma-Token-Mask
aac83258
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub