Update README.md

README.md

@@ -15,13 +15,13 @@ license_link: https://developer.download.nvidia.com/licenses/nvidia-open-model-l
 This model performs visual feature extraction.
 For instance, RADIO generates image embeddings that can be used by a downstream model to classify images.
 
-C-RADIOv2 models are available in multiple sizes:
+C-RADIOv3 models are available in multiple sizes:
 * Base (90M parameters).
 * Large (320M parameters).
-* Huge (653M parameters).
+* Huge (653M parameters). (In training)
 * Gigantic (1.1B parameters).
 
-C-RADIOv2 was trained for 1M steps (400k more steps than v1), using inverse frequency sampling for data balancing, and [PHI Standardization](https://arxiv.org/abs/2410.01680) for teacher distribution balancing.
+C-RADIOv3 was trained for 1M steps (400k more steps than v1), using inverse frequency sampling for data balancing, and [PHI Standardization](https://arxiv.org/abs/2410.01680) for teacher distribution balancing. As well as new techniques for summary distribution matching, and domain generalization.
 
 This model is ready for commercial/non-commercial use.
 
@@ -82,7 +82,7 @@ import torch
 from PIL import Image
 from transformers import AutoModel, CLIPImageProcessor
 
-hf_repo = "nvidia/C-RADIOv2-L"
+hf_repo = "nvidia/C-RADIOv3-g"
 
 image_processor = CLIPImageProcessor.from_pretrained(hf_repo)
 model = AutoModel.from_pretrained(hf_repo, trust_remote_code=True)
@@ -128,17 +128,17 @@ The resulting tensor will have shape `(B,D,H,W)`, as is typically seen with comp
 
 ## Model Version(s)
 
-* C-RADIOv2-B (90M parameters).
-* C-RADIOv2-L (320M parameters).
-* C-RADIOv2-H (653M parameters).
-* C-RADIOv2-G (1.8B parameters).
+* C-RADIOv3-B (90M parameters).
+* C-RADIOv3-L (320M parameters).
+* C-RADIOv3-H (653M parameters).
+* C-RADIOv3-g (1.2B parameters).
 
 **Links:**
 
-* https://huggingface.co/nvidia/C-RADIOv2-B
-* https://huggingface.co/nvidia/C-RADIOv2-L
-* https://huggingface.co/nvidia/C-RADIOv2-H
-* https://huggingface.co/nvidia/C-RADIOv2-g
+* https://huggingface.co/nvidia/C-RADIOv3-B
+* https://huggingface.co/nvidia/C-RADIOv3-L
+* https://huggingface.co/nvidia/C-RADIOv3-H
+* https://huggingface.co/nvidia/C-RADIOv3-g
 
 # Training and Evaluation Datasets