timm (pytorch-image-models)

Hardened pickle loading against security concerns, fixed a ZeroDivisionError in AverageMeter, and fixed reg_token not being added to no-weight-decay and stem/embed LR groups. Also added EUPE ViT (DINOv3-style) and TIPSv2 (DINOv2-style) model definitions with pretrained weights, improved optimizer torch.compile support, and extended NaFlexViT patch-layout and forward_intermediates support.

Gemma4 ViT encoders with NaFlex pipeline support for variable aspect ratio and size per image are now available, along with DINOv3 weights support in NaFlexVit. Fixed performance regressions with torch.compile and Tasks, and improved Muon optimizer fallback learning rate handling.

March 23, 2026

• Improve pickle checkpoint handling security. Default all loading to weights_only=True, add safe_global for ArgParse.
• Improve attention mask handling for core ViT/EVA models & layers. Resolve bool masks, pass is_causal through for SSL tasks.
• Fix…

Feb 23, 2026

• Add token distillation training support to distillation task wrappers
• Remove some torch.jit usage in prep for official deprecation
• Caution added to AdamP optimizer
• Call reset_parameters() even if meta-device init so that buffers get init w/ hacks like…

Jan 5 & 6, 2025

• Patch Release 1.0.24 (fix for 1.0.23)
• Add new benchmark result csv files for inference timing on all models w/ RTX Pro 6000, 5090, and 4090 cards w/ PyTorch 2.9.1
• Fix moved module error in deprecated timm.models.layers import path that impacts legacy…

Dec 30, 2025

• Add better NAdaMuon trained dpwee, dwee, dlittle (differential) ViTs with a small boost over previous runs
  • https://huggingface.co/timm/vit_dlittle_patch16_reg1_gap_256.sbb_nadamuon_in1k (83.24% top-1) *…

Patch release for priority LayerScale initialization regression in 1.0.21

What's Changed

• Add some weights for efficientnet_x / efficientnet_h models by @rwightman in https://github.com/huggingface/pytorch-image-models/pull/2602
• Update result csvs by @rwightman in…

Oct 16-20, 2025

• Add an impl of the Muon optimizer (based on https://github.com/KellerJordan/Muon) with customizations
  • extra flexibility and improved handling for conv weights and fallbacks for weight shapes not suited for orthogonalization
  • small speedup for NS…

Sept 21, 2025

• Remap DINOv3 ViT weight tags from lvd_1689m -> lvd1689m to match (same for sat_493m -> sat493m)
• Release 1.0.20

Sept 17, 2025

• DINOv3 (https://arxiv.org/abs/2508.10104) ConvNeXt and ViT models added. ConvNeXt models were mapped to existing…

Patch release for Python 3.9 compat break in 1.0.18

July 23, 2025

• Add set_input_size() method to EVA models, used by OpenCLIP 3.0.0 to allow resizing for timm based encoder models.
• Release 1.0.18, needed for PE-Core S & T models in OpenCLIP 3.0.0
• Fix small…

July 23, 2025

• Add set_input_size() method to EVA models, used by OpenCLIP 3.0.0 to allow resizing for timm based encoder models.
• Release 1.0.18, needed for PE-Core S & T models in OpenCLIP 3.0.0

July 21, 2025

• ROPE support added to NaFlexViT. All models…

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…

June 26, 2025

• MobileNetV5 backbone (w/ encoder only variant) for Gemma 3n image encoder
• Version 1.0.16 released

June 23, 2025

• Add F.grid_sample based 2D and factorized pos embed resize to NaFlexViT. Faster…

Feb 21, 2025

• SigLIP 2 ViT image encoders added (https://huggingface.co/collections/timm/siglip-2-67b8e72ba08b09dd97aecaf9)
  • Variable resolution / aspect NaFlex versions are a WIP
• Add 'SO150M2' ViT weights trained with SBB recipes, great results, better for ImageNet…

Jan 19, 2025

• Fix loading of LeViT safetensor weights, remove conversion code which should have been deactivated
• Add 'SO150M' ViT weights trained with SBB recipes, decent results, but not optimal shape for ImageNet-12k/1k pretrain/ft *…

Jan 9, 2025

• Add support to train and validate in pure bfloat16 or float16
• wandb project name arg added by https://github.com/caojiaolong, use arg.experiment for name
• Fix old issue w/ checkpoint saving not working on filesystem w/o hard-link support (e.g. FUSE…

Nov 28, 2024

• More optimizers
  • Add MARS optimizer (https://arxiv.org/abs/2411.10438, https://github.com/AGI-Arena/MARS)
  • Add LaProp optimizer (https://arxiv.org/abs/2002.04839, https://github.com/Z-T-WANG/LaProp-Optimizer)
  • Add masking from 'Cautious Optimizers'…

Quick turnaround from 1.0.10 to fix an error impacting 3rd party packages that still import through a deprecated path that isn't tested.

Oct 16, 2024

• Fix error on importing from deprecated path timm.models.registry, increased priority of existing deprecation warnings…

Oct 14, 2024

• Pre-activation (ResNetV2) version of 18/18d/34/34d ResNet model defs added by request (weights pending)
• Release 1.0.10

Oct 11, 2024

• MambaOut (https://github.com/yuweihao/MambaOut) model & weights added. A cheeky take on SSM vision models w/o the…

Aug 21, 2024

• Updated SBB ViT models trained on ImageNet-12k and fine-tuned on ImageNet-1k, challenging quite a number of much larger, slower models

| model | top1 | top5 | param_count | img_size | | -------------------------------------------------- | ------ | ------…