We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent ce73a2c commit 78c3724Copy full SHA for 78c3724
README.md
@@ -12,6 +12,10 @@
12
13
## What's New
14
15
+## Nov 4, 2025
16
+* Fix LayerScale / LayerScale2d init bug (init values ignored), introduced in 1.0.21. Thanks https://github.com/Ilya-Fradlin
17
+* Release 1.0.22
18
+
19
## Oct 31, 2025 🎃
20
* Update imagenet & OOD variant result csv files to include a few new models and verify correctness over several torch & timm versions
21
* EfficientNet-X and EfficientNet-H B5 model weights added as part of a hparam search for AdamW vs Muon (still iterating on Muon runs)
timm/version.py
@@ -1 +1 @@
1
-__version__ = '1.0.22.dev0'
+__version__ = '1.0.22'
0 commit comments