Add ViT-H v1.1 model

README.md

@@ -25,20 +25,28 @@ See [Github Page](https://github.com/baaivision/tokenize-anything).
 
 ### Model weights
 
-Two versions of the model are available with different image encoders.
+#### V1.1 Release Notes
+
+- Three versions of the model are available with different image encoders.
+- Use a longer pre-training and fine-tuning schedule (improved segmentation and caption performance).
+- Apply weight decay for all bias parameters (avoid FP16 overflow in QK matmul).
+- Sample point prompts from predicted mask instead of GT box during VG training.
 
 | Model | Description | Schedule | MD5 | Weights |
 | ----- | ------------| ------ | ----| ------ |
+| **tap_vit_h** | ViT-H TAP v1.1 model | (100% SA-1B, 180k), (VG, 50ep) | 4bdfb9 | [🤗 HF link](https://huggingface.co/BAAI/tokenize-anything/blob/main/models/tap_vit_h_v1_1.pkl) |
 | **tap_vit_l** | ViT-L TAP v1.1 model | (100% SA-1B, 180k), (VG, 50ep) | c1d41f | [🤗 HF link](https://huggingface.co/BAAI/tokenize-anything/blob/main/models/tap_vit_l_v1_1.pkl) |
 | **tap_vit_b** | ViT-B TAP v1.1 model | (100% SA-1B, 180k), (VG, 50ep) | 707f80 | [🤗 HF link](https://huggingface.co/BAAI/tokenize-anything/blob/main/models/tap_vit_b_v1_1.pkl) |
-| **tap_vit_l** | ViT-L TAP v1.0 model | (50% SA-1B, 90k), (VG, 25ep) | 03f8ec | [🤗 HF link](https://huggingface.co/BAAI/tokenize-anything/blob/main/models/tap_vit_l_v1_0.pkl) |
-| **tap_vit_b** | ViT-B TAP v1.0 model | (50% SA-1B, 90k), (VG, 25ep) | b45cbf | [🤗 HF link](https://huggingface.co/BAAI/tokenize-anything/blob/main/models/tap_vit_b_v1_0.pkl) |
 
-#### V1.1 Release Notes
+#### V1.0 Release Notes
 
-- Use a longer pre-training and fine-tuning schedule (improved segmentation and caption performance).
-- Apply weight decay for all bias parameters (avoid FP16 overflow in QK matmul).
-- Sample point prompts from predicted mask instead of GT box during VG training.
+- Two versions of the model are available with different image encoders.
+- Original paper results.
+
+| Model | Description | Schedule | MD5 | Weights |
+| ----- | ------------| ------ | ----| ------ |
+| **tap_vit_l** | ViT-L TAP v1.0 model | (50% SA-1B, 90k), (VG, 25ep) | 03f8ec | [🤗 HF link](https://huggingface.co/BAAI/tokenize-anything/blob/main/models/tap_vit_l_v1_0.pkl) |
+| **tap_vit_b** | ViT-B TAP v1.0 model | (50% SA-1B, 90k), (VG, 25ep) | b45cbf | [🤗 HF link](https://huggingface.co/BAAI/tokenize-anything/blob/main/models/tap_vit_b_v1_0.pkl) |
 
 ### Concept weights
 

models/tap_vit_h_v1_1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d3caabfc826ad52f2c34f4fe6f575b70189d3effe837da9cf3264d080c40227
+size 1488947633