Upload pickle due to diff vs. safetensors

As I noticed (small) differences in e.g. attention heatmaps if loading from .safetensors vs. full model pickle (.pt), I am sharing the original torch.save model. All evals / benchmarks were done on the pickle.

Long-ViT-L-14-REG-GATED-full-model-pickle.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef82f972b163b90773a1caca127180d0cd83726a16f36aa92af7559a4e090050
+size 1813039768