lucidrains
|
98cbdab5a4
|
have a language model address https://github.com/lucidrains/vit-pytorch/issues/348
1.12.3
|
2025-09-25 06:12:37 -07:00 |
|
lucidrains
|
f6bc14c81d
|
able to return embed from vit-nd-rotary
1.12.2
|
2025-09-23 07:21:34 -07:00 |
|
lucidrains
|
845c844b3b
|
add a vit nd with rotary nd, from Jerry Xiong at UIUC
1.12.1
|
2025-09-21 10:45:42 -07:00 |
|
lucidrains
|
5f2bc0c796
|
with assistance from claude (yes it did the einops equation building here), generalize to n-dimensions
1.12.0
|
2025-09-21 06:22:43 -07:00 |
|
lucidrains
|
35bf273037
|
1.11.7
1.11.7
|
2025-08-17 18:07:42 -07:00 |
|
Baraa sameeh
|
1123063a5e
|
Make all CCT regularization parameters user-configurable. (#346)
|
2025-08-17 18:07:25 -07:00 |
|
lucidrains
|
f8bec5ede2
|
able to project the image embedding before applying time positional embedding for accept video wrapper
1.11.6
|
2025-08-13 10:15:18 -07:00 |
|
lucidrains
|
297e7d00a2
|
handle channel first for accept video wrapper
1.11.5
|
2025-08-03 08:29:40 -07:00 |
|
lucidrains
|
29ac8e143c
|
fix when video time seq len less than max time seq len for video acceptor
1.11.4
|
2025-07-27 09:00:56 -07:00 |
|
lucidrains
|
e05cd6d8b8
|
some models only return embeddings with some kwarg on forward
1.11.3
|
2025-07-27 08:46:43 -07:00 |
|
lucidrains
|
b46233c3d6
|
need to be able to invoke with eval no grad
1.11.2
|
2025-07-27 08:25:58 -07:00 |
|
lucidrains
|
68e13a3c7d
|
bit more flexible
1.11.1
|
2025-07-27 08:14:48 -07:00 |
|
lucidrains
|
b22dc0ecd2
|
add a wrapper for accepting video and processing the images individually, optionally able to add time positional embeddings - for use in two robotics work
1.11.0
|
2025-07-27 08:05:48 -07:00 |
|
lucidrains
|
db05a141a6
|
add the proposed jumbo vit from Fuller et al. of Carleton University
|
2025-03-05 10:50:34 -08:00 |
|
lucidrains
|
9f49a31977
|
1.9.2
1.9.2
|
2025-01-19 05:53:11 -08:00 |
|
JacobLinCool
|
ab63fc9cc8
|
remove duplicated qkv computation in na_vit_nested_tensor_3d.py (#341)
|
2025-01-19 05:52:46 -08:00 |
|
Phil Wang
|
c3018d1433
|
1.9.1
1.9.1
|
2025-01-04 07:55:49 -08:00 |
|
Kale Kundert
|
b7ed6bad28
|
add option to set frame padding for 3D CCT (#339)
|
2025-01-04 07:55:27 -08:00 |
|
lucidrains
|
e7cba9ba6d
|
add a simple vit flavor for a new bytedance paper that proposes to break out of the traditional one residual stream architecture - "hyper-connections"
|
2024-12-20 17:43:50 -08:00 |
|
lucidrains
|
56373c0cbd
|
make value residual learned
1.8.9
|
2024-11-24 08:21:28 -08:00 |
|
lucidrains
|
24196a3e8a
|
allow for qk norm to be turned off for na vit nested tensor
1.8.8
|
2024-11-20 10:59:22 -08:00 |
|
Phil Wang
|
f6d7287b6b
|
readme
|
2024-11-19 08:20:38 -08:00 |
|
lucidrains
|
d47c57e32f
|
fix tests
|
2024-11-10 09:43:54 -08:00 |
|
lucidrains
|
0449865786
|
update minimum version for nested tensor of NaViT
|
2024-11-10 09:37:48 -08:00 |
|
lucidrains
|
6693d47d0b
|
update comment for navit 3d
|
2024-11-07 20:02:07 -08:00 |
|
Phil Wang
|
141239ca86
|
fix value residual
1.8.7
|
2024-10-31 06:48:24 -07:00 |
|
lucidrains
|
0b5c9b4559
|
add value residual based simple vit
1.8.6
|
2024-10-28 09:19:00 -07:00 |
|
lucidrains
|
e300cdd7dc
|
fix multiheaded qk rmsnorm in nViT
1.8.5
|
2024-10-10 19:15:17 -07:00 |
|
Phil Wang
|
36ddc7a6ba
|
go all the way with the normalized vit, fix some scales
1.8.4
|
2024-10-10 10:42:37 -07:00 |
|
Phil Wang
|
1d1a63fc5c
|
cite for hypersphere vit adapted from ngpt
|
2024-10-10 10:15:04 -07:00 |
|
Phil Wang
|
74b62009f8
|
go for multi-headed rmsnorm for the qknorm on hypersphere vit
1.8.2
|
2024-10-10 08:09:58 -07:00 |
|
Phil Wang
|
f50d7d1436
|
add a hypersphere vit, adapted from https://arxiv.org/abs/2410.01131
1.8.1
|
2024-10-09 07:32:25 -07:00 |
|
lucidrains
|
82f2fa751d
|
address https://github.com/lucidrains/vit-pytorch/issues/330
1.7.14
|
2024-10-04 07:01:48 -07:00 |
|
lucidrains
|
fcb9501cdd
|
add register tokens to the nested tensor 3d na vit example for researcher
1.7.12
|
2024-08-28 12:21:31 -07:00 |
|
lucidrains
|
c4651a35a3
|
1.7.11
1.7.11
|
2024-08-21 19:24:13 -07:00 |
|
roydenwa
|
9d43e4d0bb
|
Add ViViT variant with factorized self-attention (#327)
* Add FactorizedTransformer
* Add variant param and check in fwd method
* Check if variant is implemented
* Describe new ViViT variant
|
2024-08-21 19:23:38 -07:00 |
|
Phil Wang
|
5e808f48d1
|
3d version of navit nested tensor
1.7.10
|
2024-08-21 07:23:21 -07:00 |
|
Phil Wang
|
bed48b5912
|
fix tests
fix tests
|
2024-08-20 15:35:04 -07:00 |
|
lucidrains
|
73199ab486
|
Nested navit (#325)
add a variant of NaViT using nested tensors
1.7.7
|
2024-08-20 15:12:29 -07:00 |
|
Phil Wang
|
4f22eae631
|
1.7.5
1.7.5
|
2024-08-07 08:46:18 -07:00 |
|
Phil Wang
|
dfc8df6713
|
add the u-vit implementation with simple vit + register tokens
|
2024-08-07 08:45:57 -07:00 |
|
lucidrains
|
9992a615d1
|
attention re-use in lookup vit should use pre-softmax attention matrix
1.7.4
|
2024-07-19 19:23:38 -07:00 |
|
Phil Wang
|
4b2c00cb63
|
when cross attending in look vit, make sure context tokens are normalized
1.7.3
|
2024-07-19 10:23:12 -07:00 |
|
Phil Wang
|
ec6c48b8ff
|
norm not needed when reusing attention in lookvit
1.7.2
|
2024-07-19 10:00:03 -07:00 |
|
Phil Wang
|
547bf94d07
|
1.7.1
1.7.1
|
2024-07-19 09:49:44 -07:00 |
|
Phil Wang
|
bd72b58355
|
add lookup vit, cite, document later
|
2024-07-19 09:48:58 -07:00 |
|
lucidrains
|
e3256d77cd
|
fix t2t vit having two layernorms, and make final layernorm in distillation wrapper configurable, default to False for vit
1.7.0
|
2024-06-11 15:12:53 -07:00 |
|
lucidrains
|
90be7233a3
|
rotary needs to be done with full precision to be safe
1.6.9
|
2024-05-11 08:04:32 -07:00 |
|
Phil Wang
|
bca88e9039
|
address https://github.com/lucidrains/vit-pytorch/issues/300
1.6.8
|
2024-05-02 08:46:39 -07:00 |
|
Phil Wang
|
96f66d2754
|
address https://github.com/lucidrains/vit-pytorch/issues/306
1.6.7
|
2024-04-18 09:44:29 -07:00 |
|