Sourced from timm's releases.

Release v1.0.17

July 7, 2025

• MobileNet-v5 backbone tweaks for improved Google Gemma 3n behaviour (to pair with updated official weights)
  • Add stem bias (zero'd in updated weights, compat break with old weights)
  • GELU -> GELU (tanh approx). A minor change to be closer to JAX
• Add two arguments to layer-decay support, a min scale clamp and 'no optimization' scale threshold
• Add 'Fp32' LayerNorm, RMSNorm, SimpleNorm variants that can be enabled to force computation of norm in float32
• Some typing, argument cleanup for norm, norm+act layers done with above
• Support Naver ROPE-ViT (https://github.com/naver-ai/rope-vit) in eva.py, add RotaryEmbeddingMixed module for mixed mode, weights on HuggingFace Hub

model	img_size	top1	top5	param_count
vit_large_patch16_rope_mixed_ape_224.naver_in1k	224	84.84	97.122	304.4
vit_large_patch16_rope_mixed_224.naver_in1k	224	84.828	97.116	304.2
vit_large_patch16_rope_ape_224.naver_in1k	224	84.65	97.154	304.37
vit_large_patch16_rope_224.naver_in1k	224	84.648	97.122	304.17
vit_base_patch16_rope_mixed_ape_224.naver_in1k	224	83.894	96.754	86.59
vit_base_patch16_rope_mixed_224.naver_in1k	224	83.804	96.712	86.44
vit_base_patch16_rope_ape_224.naver_in1k	224	83.782	96.61	86.59
vit_base_patch16_rope_224.naver_in1k	224	83.718	96.672	86.43
vit_small_patch16_rope_224.naver_in1k	224	81.23	95.022	21.98
vit_small_patch16_rope_mixed_224.naver_in1k	224	81.216	95.022	21.99
vit_small_patch16_rope_ape_224.naver_in1k	224	81.004	95.016	22.06
vit_small_patch16_rope_mixed_ape_224.naver_in1k	224	80.986	94.976	22.06

• Some cleanup of ROPE modules, helpers, and FX tracing leaf registration
• Preparing version 1.0.17 release

What's Changed

• Adding Naver rope-vit compatibility to EVA ViT by @​rwightman in huggingface/pytorch-image-models#2529
• Update no_grad usage to inference_mode if possible by @​GuillaumeErhard in huggingface/pytorch-image-models#2534
• Add a min layer-decay scale clamp, and no optimization threshold to exclude groups from optimization by @​rwightman in huggingface/pytorch-image-models#2537
• Add stem_bias option to MNV5. Resolve the norm layer so can pass string. by @​rwightman in huggingface/pytorch-image-models#2538
• Add flag to enable float32 computation for normalization (norm + affine) by @​rwightman in huggingface/pytorch-image-models#2536
• fix: mnv5 conv_stem bias and GELU with approximate=tanh by @​RyanMullins in huggingface/pytorch-image-models#2533
• Fixup casting issues for weights/bias in fp32 norm layers by @​rwightman in huggingface/pytorch-image-models#2539
• Fix H, W ordering for xy indexing in ROPE by @​rwightman in huggingface/pytorch-image-models#2541
• Fix 3 typos in README.md by @​robin-ede in huggingface/pytorch-image-models#2544

New Contributors

• @​GuillaumeErhard made their first contribution in huggingface/pytorch-image-models#2534
• @​RyanMullins made their first contribution in huggingface/pytorch-image-models#2533
• @​robin-ede made their first contribution in huggingface/pytorch-image-models#2544

Full Changelog: https://github.com/huggingface/pytorch-image-models/compare/v1.0.16...v1.0.17

• 59fdbaa Fix 3 typos in README.md
• 7452176 Remove debug print from mnv5 enc module
• 2171831 Fix scripting?
• 33791c8 Fix H, W ordering for xy indexing in ROPE, impacts models w/ xy indexing and ...
• a7c5368 Update README, bump version to 1.0.17 in prep for release
• 37d9440 Fixup casting issues for weights/bias in fp32 norm layers
• ea4f940 fix: mnv5 with conv_stem bias and GELU approx tanh
• 446e8a8 Add flag to enable float32 computation for normalization (norm + affine) (#2536)
• 168137b Merge pull request #2538 from huggingface/mnv5_bias_str_norm
• e1c158e Add stem_bias option to MNV5. Resolve the norm layer so can pass string args....
• Additional commits viewable in compare view

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)