Timm ❤️ Transformers: Use any timm model with transformers
•
24
Ross Wightman
rwightman
AI & ML interests
Computer vision, transfer learning, semi/self supervised learning, robotics.
Recent Activity
upvoted
an
article
about 9 hours ago
MiniMax-01 is Now Open-Source: Scaling Lightning Attention for the AI Agent Era
posted
an
update
about 12 hours ago
I re-worked the JuptyerLab Space template recently. It's optimized for `timm` use, but will work great with `transformers` and other libs. Updated the base image, Python 3.12, Pillow-SIMD before better CPU use with image preprocessing, and made a number of other tweaks. From the Jupyter launcher you can run the terminal and setup a `timm` environment in moments with `setup_timm_dev` or `setup_timm_scripts` helpers. Give it a try, https://huggingface.co/spaces/timm/jupyterlab-timm
updated
a model
1 day ago
timm/ese_vovnet57b.ra4_e3600_r256_in1k
Articles
Organizations
Posts
14
Post
323
I re-worked the JuptyerLab Space template recently. It's optimized for
timm use, but will work great with transformers and other libs. Updated the base image, Python 3.12, Pillow-SIMD before better CPU use with image preprocessing, and made a number of other tweaks. From the Jupyter launcher you can run the terminal and setup a timm environment in moments with setup_timm_dev or setup_timm_scripts helpers. Give it a try,
timm/jupyterlab-timm
Post
1081
New
* PaliGemma2 encoders (ported from google/paligemma-2-release-67500e1e1dbfdd4dee27ba48)
* AIMv-2 encoders (ported from apple/aimv2-6720fe1558d94c7805f7688c)
A few higher resolution 384x384 ConvNeXt-Nano ImageNet-12k pretrain & finetunes. See other changes here: https://github.com/huggingface/pytorch-image-models/releases/tag/v1.0.13
And support added in both
* DFN CLIP L/14 w/ 39B samples seen - apple/DFN2B-CLIP-ViT-L-14-39B, timm/vit_large_patch14_clip_224.dfn2b_s39b
* MetaCLIP H/14 (altogether) - timm/vit_huge_patch14_clip_224.metaclip_altogether
And last, ~70-80 models that were relying on
timm 1.0.13 and OpenCLIP 2.30.0 releases to start the year. Both modest but worthwhile updates.timm added a number of new model weights, supporting loading of: * PaliGemma2 encoders (ported from google/paligemma-2-release-67500e1e1dbfdd4dee27ba48)
* AIMv-2 encoders (ported from apple/aimv2-6720fe1558d94c7805f7688c)
A few higher resolution 384x384 ConvNeXt-Nano ImageNet-12k pretrain & finetunes. See other changes here: https://github.com/huggingface/pytorch-image-models/releases/tag/v1.0.13
And support added in both
OpenCLIP and timm for two CLIP models that were missed. The DFN L/14 is 🔥* DFN CLIP L/14 w/ 39B samples seen - apple/DFN2B-CLIP-ViT-L-14-39B, timm/vit_large_patch14_clip_224.dfn2b_s39b
* MetaCLIP H/14 (altogether) - timm/vit_huge_patch14_clip_224.metaclip_altogether
And last, ~70-80 models that were relying on
timm remapping from OpenCLIP got their own timm hub instances to allow use with the upcoming Transformers TimmWrapperModel
Collections
1
Fine-tune experiments for various `timm` models on the INaturalist 2021 Challenge dataset (https://github.com/visipedia/inat_comp/tree/master/2021)
-
timm/eva02_large_patch14_clip_336.merged2b_ft_inat21
Image Classification • Updated • 4 • 11 -
timm/vit_large_patch14_clip_336.datacompxl_ft_augreg_inat21
Image Classification • Updated • 1 • 1 -
timm/vit_large_patch14_clip_336.laion2b_ft_augreg_inat21
Image Classification • Updated • 9 -
timm/vit_large_patch14_clip_336.datacompxl_ft_inat21
Image Classification • Updated • 65 • 1
