You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+4Lines changed: 4 additions & 0 deletions
Original file line number
Diff line number
Diff line change
@@ -24,6 +24,10 @@ And a big thanks to all GitHub sponsors who helped with some of my costs before
24
24
* ❗Updates after Oct 10, 2022 are available in 0.8.x pre-releases (`pip install --pre timm`) or cloning main❗
25
25
* Stable releases are 0.6.x and available by normal pip install or clone from [0.6.x](https://github.com/rwightman/pytorch-image-models/tree/0.6.x) branch.
26
26
27
+
### Feb 20, 2023
28
+
* Add 320x320 `convnext_large_mlp.clip_laion2b_ft_320` and `convnext_lage_mlp.clip_laion2b_ft_soup_320` CLIP image tower weights for features & fine-tune
29
+
* 0.8.13dev0 pypi release for latest changes w/ move to huggingface org
30
+
27
31
### Feb 16, 2023
28
32
*`safetensor` checkpoint support added
29
33
* Add ideas from 'Scaling Vision Transformers to 22 B. Params' (https://arxiv.org/abs/2302.05442) -- qk norm, RmsNorm, parallel block
0 commit comments