Raushan Turganbay 5b6f170abc Better and more extensive tests for RoPE (#46912) ...

* fix

* test

* tmp

* !

* fix

* .

* multimodal rope as well, just copy

* expectations

* missing device in init, should follow Llama for text rope!

* Revert "fix"

This reverts commit 7023cfa6ed.

* Revert "test"

This reverts commit ab6e25ebc5.

* delete and move a lot of things

* and this, should not skip

* fix a bunch

* small batch of fixes

* skip a bunch of audio models, they need special/fixes audio sizes and can't really support scaled rope

* fix copies

* now fix?

* check text config

* dont skip, was fixed at some point magically

* more comments

* Add more nesting! add per layer config though we defi need to merge it with nested rope, that is too many fallbacks

* kmp, per-layer config is not compatible with DS4

* wtf?!

2026-07-27 11:03:06 +00:00

..

__init__.py

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

2025-07-15 10:40:41 +02:00

test_modeling_modernbert_decoder.py

Better and more extensive tests for RoPE (#46912)

2026-07-27 11:03:06 +00:00