Add in12k fine-tuned convnext_xxlarge

Author: rwightman

README.md

@@ -31,6 +31,7 @@
 * DINOv2 'register' ViT model weights added
 * Add `quickgelu` ViT variants for OpenAI, DFN, MetaCLIP weights that use it (less efficient)
 * Improved typing added to ResNet, MobileNet-v3 thanks to [Aryan](https://github.com/a-r-r-o-w)
+* ImageNet-12k fine-tuned (from LAION-2B CLIP) `convnext_xxlarge`
 * 0.9.9 release
 
 ### Oct 20, 2023

timm/models/convnext.py

@@ -828,6 +828,10 @@ def _cfgv2(url='', **kwargs):
         hf_hub_id='timm/',
         mean=OPENAI_CLIP_MEAN, std=OPENAI_CLIP_STD, num_classes=11821,
         input_size=(3, 384, 384), pool_size=(12, 12), crop_pct=1.0, crop_mode='squash'),
+    'convnext_xxlarge.clip_laion2b_soup_ft_in12k': _cfg(
+        hf_hub_id='timm/',
+        mean=OPENAI_CLIP_MEAN, std=OPENAI_CLIP_STD, num_classes=11821,
+        input_size=(3, 256, 256), pool_size=(8, 8), crop_pct=1.0),
 
     # CLIP original image tower weights
     'convnext_base.clip_laion2b': _cfg(