Add new #1 top-performing smooth-GmP model
Browse filesFine-tuned with GmP on COCO-SPRIGHT-40k as before, BUT with new a custom loss function and label smoothing: This CLIP has >91% accuracy on ImageNet/ObjectNet!
ViT-L-14-BEST-smooth-GmP-ft-pickle-OpenAI.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2135fa3c6d8f9a64e3114b673e12ca38d50c77da0204ffeb34a9aeb29a7791e
|
3 |
+
size 932307905
|
ViT-L-14-BEST-smooth-GmP-ft-state_dict.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61661af02a59b5d5a175a94cba447ec5cc2318532ef202343a3be063b20981a9
|
3 |
+
size 932240142
|
ViT-L-14-BEST-smooth-GmP-ft.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fb57a8045c00fd501d9195515e94c0ae339d0fb9f46dc76cb20e685886494d9
|
3 |
+
size 932103308
|