Ross Wightman
|
ea728f67fa
|
Improve several typing issues for flex vit, can (almost) work with jit if we bash h,w key into an int or str
|
2025-04-14 11:01:56 -07:00 |
|
Ross Wightman
|
b4bb0f452a
|
Exclude embeds module and mask attn functions from tracing
|
2025-04-09 15:34:15 -07:00 |
|
Ross Wightman
|
13e0f3a4a3
|
Add loss scale arg, initial distributed loss scale. Maybe fix FX for the model.
|
2025-04-08 20:47:57 -07:00 |
|
Ross Wightman
|
6675590264
|
Fix ParallelThingsBlock w/ attn_mask
|
2025-04-08 09:35:34 -07:00 |
|
Ross Wightman
|
0893f5d296
|
Initial NaFlex ViT model and training support
|
2025-04-07 21:27:10 -07:00 |
|
Adam J. Stewart
|
92682d8d4d
|
timm.models: explicitly export attributes
|
2025-02-21 14:19:39 -08:00 |
|
Ross Wightman
|
a667d3d8f0
|
siglip2 weights on hub, fix forward_intermediates when no prefix tokens (& return prefix selected)
|
2025-02-21 13:10:51 -08:00 |
|
Ross Wightman
|
f63a11cf81
|
Remove duplicate so400m/16 @ 256 model def
|
2025-02-21 13:10:51 -08:00 |
|
Ross Wightman
|
9758e0b8b0
|
Prep for siglip2 release
|
2025-02-21 13:10:51 -08:00 |
|
Adam J. Stewart
|
c68d724e9c
|
adapt_input_conv: add type hints
|
2025-02-21 12:28:22 -08:00 |
|
Ross Wightman
|
7234f5c6c5
|
Add 448 so150m2 weight/model, add updated internvit 300m weight
|
2025-02-17 12:59:10 -08:00 |
|
Ross Wightman
|
9ce824c39a
|
Add vit so150m2 weights
|
2025-02-14 15:55:51 -08:00 |
|
Ryan
|
17eabaad17
|
Fix RDNet forward call
|
2025-01-21 11:52:05 -08:00 |
|
Ryan
|
80a4877376
|
Fix self.reset_classifier num_classes update
|
2025-01-21 11:52:05 -08:00 |
|
Ross Wightman
|
aa333079da
|
Tweak so150m2 def
|
2025-01-19 13:40:53 -08:00 |
|
Josua Rieder
|
8d81fdf3d9
|
Fix typos
|
2025-01-19 13:39:40 -08:00 |
|
Ross Wightman
|
3677f67902
|
Add the 256x256 in1k ft of the so150m, add an alternate so150m def
|
2025-01-18 15:51:57 -08:00 |
|
Ross Wightman
|
2a84d68d02
|
Add some so150m vit w/ sbb recipe weights, and a ese_vovnet57b model with RA4 recipe
|
2025-01-18 15:51:57 -08:00 |
|
Ross Wightman
|
9265d54a3a
|
LeViT safetensors load is broken by conversion code that wasn't deactivated
|
2025-01-16 11:37:00 -08:00 |
|
Adam J. Stewart
|
6d21eb0d37
|
VGG ConvMlp: fix layer defaults/types
|
2025-01-15 12:11:56 +01:00 |
|
Adam J. Stewart
|
f5c4d5cbb7
|
Add missing imports
|
2025-01-11 15:13:16 +01:00 |
|
Adam J. Stewart
|
19aaea3c8f
|
Fix nn.Module type hints
|
2025-01-11 15:09:21 +01:00 |
|
Ross Wightman
|
155f6e7fea
|
Update README, few minor fixups.
|
2025-01-06 13:09:15 -08:00 |
|
Ross Wightman
|
2b251fb291
|
Wrap torch checkpoint() fn to default use_reentrant flag to False and allow env var override
|
2025-01-06 11:28:39 -08:00 |
|
Ross Wightman
|
e846b2cf28
|
Add 384x384 in12k pretrain and finetune for convnext_nano
|
2024-12-31 13:16:43 -08:00 |
|
Ross Wightman
|
b0068ba5d0
|
Switch hf hub entries for new aimv2 / dfn weights to point to timm locations. Undo forced device for SDR linspace, part of another change.
|
2024-12-30 19:24:21 -08:00 |
|
Ross Wightman
|
1bf84b35c3
|
Update tests for aimv2 filtering
|
2024-12-30 19:24:21 -08:00 |
|
Ross Wightman
|
b33418713a
|
Add (almost) full set of aimv2 model instances. Switch back to unpacked SwiGLU. Verify correctness. Add DFN L/14 39B weight.
|
2024-12-30 19:24:21 -08:00 |
|
Ross Wightman
|
5f12a25114
|
Add bias arg to Vitamin GeGLU
|
2024-12-30 19:24:21 -08:00 |
|
Ross Wightman
|
5804d92e4b
|
Switch aimv2 to used packed SwiGLU
|
2024-12-30 19:24:21 -08:00 |
|
Ross Wightman
|
15406a939e
|
Fixing RmsNorm to fix #2380 and noticed with aimv2 when comparing outputs. Still some work to do, need to look at AMP / fast mode behaviour, dispatch to torch when possible. Add SimpleNorm for 'LayerNorm w/o centering and bias'
|
2024-12-30 19:24:21 -08:00 |
|
Ross Wightman
|
a648a04834
|
Supporting aimv2 encoders
|
2024-12-30 19:24:21 -08:00 |
|
Ross Wightman
|
790decc89b
|
Add more pali(2) weights. Switch rest of models adapting open_clip weights to their own weight instances.
|
2024-12-27 14:00:41 -08:00 |
|
Ross Wightman
|
01cf0f72af
|
Add support for tag, license customization through push_to_hub
|
2024-12-27 14:00:41 -08:00 |
|
Ross Wightman
|
b12ecbd614
|
Move siglip timm weights to own repos
|
2024-12-27 14:00:41 -08:00 |
|
Ross Wightman
|
6fb7aaf37d
|
Switching to timm specific weight instances for open_clip image encoders to facilitate hf-hub: use in timm and new transformers TimmWrapper
|
2024-12-27 14:00:41 -08:00 |
|
Ryan
|
ab0a70dfff
|
fix feature_info.reduction
|
2024-12-18 21:12:40 +08:00 |
|
Álvaro Justen (@turicas)
|
9383f2880d
|
Add cache_dir example
|
2024-12-06 10:39:13 -08:00 |
|
Ross Wightman
|
d1e9a8622a
|
Rename inception_next_atto pretrained str
|
2024-12-06 10:36:47 -08:00 |
|
Weihao Yu
|
0576175d85
|
Add inception_next_atto
|
2024-12-06 10:36:47 -08:00 |
|
Ross Wightman
|
7ab2b938e5
|
More tweaks to docstrings for hub/builder
|
2024-12-06 10:25:06 -08:00 |
|
Ross Wightman
|
dc1bb05e8e
|
Punch cache_dir through model factory / builder / pretrain helpers. Improve some annotations in related code.
|
2024-12-06 10:25:06 -08:00 |
|
Ross Wightman
|
5fe5f9d488
|
Add a different mnv4 conv-small weight
|
2024-12-02 16:14:37 -08:00 |
|
Johannes
|
093a234d01
|
Update torchvision resnet legacy weight urls in resnet.py
|
2024-11-26 15:53:54 +01:00 |
|
Ross Wightman
|
900d2b508d
|
add mnv4 conv_medium in12k -> in1k ft
|
2024-11-22 16:31:45 -08:00 |
|
Ross Wightman
|
6bcbdbfe41
|
CS3-DarkNet Small (Focus) w/ RA4 recipe. Fix #2122
|
2024-11-22 16:31:45 -08:00 |
|
Ross Wightman
|
ae0737f5d0
|
Typo
|
2024-11-17 13:54:50 -08:00 |
|
Ross Wightman
|
84049d7f1e
|
Missed input_size pretraind_cfg metadata for v2 34d @ 384
|
2024-11-17 12:44:08 -08:00 |
|
Ross Wightman
|
b7a4b49ae6
|
Add some 384x384 small model weights, 3 variants of mnv4 conv medium on in12k pretrain, and resnetv2-34d on in1k
|
2024-11-17 12:14:39 -08:00 |
|
Wojtek Jasiński
|
eb94efb218
|
fix pos embed dynamic resampling for eva
|
2024-11-06 16:03:27 -08:00 |
|