add the proposed jumbo vit from Fuller et al. of Carleton University

add the proposed jumbo vit from Fuller et al. of Carleton University

add the proposed jumbo vit from Fuller et al. of Carleton University

1.9.2

remove duplicated qkv computation in na_vit_nested_tensor_3d.py (#341)

1.9.1

add option to set frame padding for 3D CCT (#339)

add a simple vit flavor for a new bytedance paper that proposes to br…

add a simple vit flavor for a new bytedance paper that proposes to br…

make value residual learned

allow for qk norm to be turned off for na vit nested tensor

readme

fix tests

try again

update minimum version for nested tensor of NaViT

update comment for navit 3d

fix value residual

add value residual based simple vit

fix multiheaded qk rmsnorm in nViT

go all the way with the normalized vit, fix some scales

go all the way with the normalized vit, fix some scales

cite for hypersphere vit adapted from ngpt

go for multi-headed rmsnorm for the qknorm on hypersphere vit

add a hypersphere vit, adapted from https://arxiv.org/abs/2410.01131

add a hypersphere vit, adapted from https://arxiv.org/abs/2410.01131

add a hypersphere vit, adapted from https://arxiv.org/abs/2410.01131

address #330

add register tokens to the nested tensor 3d na vit example for resear…