Skip to content

Commit 9f16d68

Browse files
authored
Update README.md
1 parent 7f8fd8a commit 9f16d68

File tree

1 file changed

+11
-0
lines changed

1 file changed

+11
-0
lines changed

README.md

Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -12,6 +12,17 @@
1212

1313
## What's New
1414

15+
## Dec 12, 2025
16+
* Add CSATV2 model (thanks https://github.com/gusdlf93) -- a lightweight but high res model with DCT stem & spatial attention. https://huggingface.co/Hyunil/CSATv2
17+
* Add AdaMuon and NAdaMuon optimizer support to existing `timm` Muon impl. Appears more competitive vs AdamW with familiar hparams for image tasks.
18+
* End of year PR cleanup, merge aspects of several long open PR
19+
* Merge differential attention (`DiffAttention`), add corresponding `DiffParallelScalingBlock` (for ViT), train some wee vits
20+
* https://huggingface.co/timm/vit_dwee_patch16_reg1_gap_256.sbb_in1k
21+
* https://huggingface.co/timm/vit_dpwee_patch16_reg1_gap_256.sbb_in1k
22+
* Add a few pooling modules, `LsePlus` and `SimPool`
23+
* Cleanup, optimize `DropBlock2d` (also add support to ByobNet based models)
24+
* Bump unit tests to PyTorch 2.9.1 + Python 3.13 on upper end, lower still PyTorch 1.13 + Python 3.10
25+
1526
## Dec 1, 2025
1627
* Add lightweight task abstraction, add logits and feature distillation support to train script via new tasks.
1728
* Remove old APEX AMP support

0 commit comments

Comments
 (0)