transformers
Add ModernBERT Decoder Models - ModernBERT, but trained with CLM!
#38967
Merged

Add ModernBERT Decoder Models - ModernBERT, but trained with CLM! #38967

ArthurZucker merged 32 commits into huggingface:main from modernbertdecoder
orionw
working locally; need to style and test
fc179b1c
added docs and initial tests; need to debug and flesh out
9c3838d0
fixed tests
2574d9b1
working long context; batches
ac30deed
working fa2 and eager
c1e9a766
update tests
506633f5
add missing confnigs
8bf43687
remove default autoset
8c90812a
fix spacing
c865c1d8
fix most tests
b1ef0868
fixed tests
9de1db1e
fix to init
0455ecaf
orionw
Rocketknight1
orionw
orionw
ArthurZucker
ArthurZucker commented on 2025-06-25
jbdel
refactor to match new transformers updates
128fe5ea
remove static cache option
0fb86605
fa2 fix
ca84ac90
orionw Merge branch 'main' into modernbertdecoder
25895f78
orionw
orionw
fix docs
07f5a194
orionw Merge branch 'main' into modernbertdecoder
8afc9cad
ArthurZucker
orionw
ArthurZucker
ArthurZucker commented on 2025-07-08
in progress
bac6822e
orionw Merge branch 'main' into modernbertdecoder
3d7808c1
working on tests
17c8b08f
fixed issue with attn outputs
ce8363f7
remove debug
4b5182e9
fix local config attr
80186ca5
update doc string
65245f39
fix docstring
ba6b351d
orionw
orionw commented on 2025-07-10
add docs to toc
cd453f74
correct typo in toc
fa6b2f4d
orionw Merge branch 'main' into modernbertdecoder
27b4a092
add new updates from main w.r.t. ModernBERT RoPE
9d4f6200
fix local param
099342da
orionw
orionw Merge branch 'main' into modernbertdecoder
dd563a6e
github-actions
orionw
ArthurZucker
ArthurZucker approved these changes on 2025-07-15
ArthurZucker ArthurZucker merged 0e4b7938 into main 201 days ago
orionw

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone