transformers
Add the Bamba Model
#34982
Merged

Add the Bamba Model #34982

molbap merged 44 commits into huggingface:main from fabianlim:bamba-pr
fabianlim
fabianlim fabianlim marked this pull request as draft 1 year ago
fabianlim fabianlim changed the title initial commit for PR Add the Bamba Model 1 year ago
fabianlim initial commit for PR
e2991328
fabianlim fabianlim force pushed to e2991328 1 year ago
fabianlim rename dynamic cache
c1d2d2b4
Rocketknight1
fabianlim
raghukiran1224
Rocketknight1
Rocketknight1 Rocketknight1 assigned molbap molbap 1 year ago
fabianlim add more unit tests
7c87f858
fabianlim add integration test
2897866a
fabianlim add integration test
5671778d
ani300 Add modular bamba file
947b877f
ani300 Merge branch 'bamba-pr' of https://github.com/fabianlim/transformers …
78c9b04b
ani300 Merge branch 'main' into bamba-pr
3e352f72
ani300 Remove trainer changes from unrelated PR
2c215721
ani300 Modify modular and cofig to get model running
a0e58b4c
molbap molbap added State space models
molbap molbap added New model
ani300 Fix some CI errors and beam search
a450f1c8
ani300 Fix a plethora of bugs from CI/docs/etc
146a940c
ani300 Add bamba to models with special caches
1144bbbd
ani300 Updat to newer mamba PR for mamba sublayer
856cb3a4
fabianlim fix test_left_padding_compatibility
9ec6d15d
fabianlim Merge remote-tracking branch 'upstream/main' into bamba-pr
d7875bef
fabianlim fix style
895521df
fabianlim fix remaining tests
a394a7d6
fabianlim missed this test
f0604de7
fabianlim ran make style
92ad669d
molbap molbap added run-slow
fabianlim move slow tag to integration obj
36370f32
fabianlim make style
ecd7aff8
molbap
molbap commented on 2024-12-16
fabianlim address comments
94a13d6b
fabianlim fix modular
4cff28c8
fabianlim left out one part of modular
5d9ce5c5
fabianlim change model
b934261c
fabianlim fabianlim marked this pull request as ready for review 1 year ago
ani300 Make Rotary modular as well
024072ac
ani300 Merge branch 'main' into bamba-pr
f7ceb0cb
molbap
molbap approved these changes on 2024-12-16
divya-kumari32 Update bamba.md
0e97747f
divya-kumari32 Update bamba.md
53b8acfc
divya-kumari32 Update bamba.md
a8fa7ff6
divya-kumari32 Update bamba.md
0115bf6c
ani300 Merge pull request #4 from divya-kumari32/patch-1
44788dce
ani300 Add docs for config and model back
537964b4
ani300 Merge branch 'main' into bamba-pr
ab261616
ani300 Add warning when using fast kernels
ddd61182
fabianlim replaced generate example
10887780
pcuenca pcuenca requested a review from ArthurZucker ArthurZucker 1 year ago
ArthurZucker
ArthurZucker approved these changes on 2024-12-18
ani300 Address comments from PR
d4c650ca
ani300 Merge branch 'bamba-pr' of https://github.com/fabianlim/transformers …
6f28b96f
ani300 Merge branch 'main' into bamba-pr
1c82bf06
ani300 Propagate attention fixes
9911cdf1
ani300 Fix attention interfaces to the new API
c7b50e60
ani300 Fix API for decoder layer
e0f34f57
ani300 Remove extra weights
bdd32720
molbap molbap merged 9613933b into main 1 year ago
ArthurZucker

Login to write a write a comment.

Login via GitHub

Assignees
Labels
Milestone