Add sam_vit_l_0b3195.safetensors (bitwise copy of the upstream ViT-L checkpoint); card

README.md

@@ -20,6 +20,7 @@ encoder and mask decoder.
 | File | Image encoder |
 |------|---------------|
 | `sam_vit_b_01ec64.safetensors` | ViT-B |
+| `sam_vit_l_0b3195.safetensors` | ViT-L |
 
 ## Provenance
 
@@ -30,8 +31,9 @@ from either file has a bitwise-identical `state_dict()` and gives bitwise-identi
 | File | Upstream source | Source sha256 | sha256 |
 |------|-----------------|---------------|--------|
 | `sam_vit_b_01ec64.safetensors` | [`sam_vit_b_01ec64.pth`](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth) | `ec2df62732614e57411cdcf32a23ffdf28910380d03139ee0f4fcbe91eb8c912` | `fbf4c1ad844a2e9b867d89dc04a61f3ece19c57ebb7d8fcb6da92062a291d839` |
+| `sam_vit_l_0b3195.safetensors` | [`sam_vit_l_0b3195.pth`](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_l_0b3195.pth) | `3adcc4315b642a4d2101128f611684e8734c41232a17c648ed1693702a49a622` | `8e087bc0db5cfac2676ae69bb1b846fa1f6cc193fc0beb6be8fb14fc7406be41` |
 
-The upstream ViT-B checkpoint stores `mask_decoder.iou_token.weight` and `mask_decoder.mask_tokens.weight` as views
+The upstream ViT-B and ViT-L checkpoints store `mask_decoder.iou_token.weight` and `mask_decoder.mask_tokens.weight` as views
 of one shared storage. The safetensors format forbids shared storage, so each is stored as its own copy with identical
 values; loading a model copies them into separate parameters either way.
 

sam_vit_l_0b3195.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e087bc0db5cfac2676ae69bb1b846fa1f6cc193fc0beb6be8fb14fc7406be41
+size 1249427848