Initial upload via tools/push_to_hf.py (architecture: ilex.models.triad.TriadPlainConvUNet)

README.md

@@ -0,0 +1,65 @@
+---
+library_name: ilex
+tags:
+- jax
+- equinox
+- ilex
+- neuroimaging
+- 3d-mri
+license: mit
+license_link: https://github.com/wangshansong1/Triad/blob/main/LICENSE
+---
+
+# Triad (3D-MRI self-supervised foundation backbone) -- Triad PlainConvUNet encoder (SimMIM-pretrained)
+
+## Description
+
+Triad vision foundation model for 3D MRI, ported to JAX / Equinox from the upstream PyTorch release. Triad is an nnUNet PlainConvEncoder pretrained self-supervised on Triad-131K (131,170 3D MRI volumes spanning brain, breast, and prostate; T1/T2/FLAIR/DWI/fMRI/DCE) and serves as a transfer-learning backbone for downstream MRI segmentation, classification, and registration. The published checkpoints are encoder-only (the self-supervised decoder / mask token are stripped); this port exposes the pretrained encoder, whose multi-scale skip features are the transfer representation. Two pretraining objectives are released as separate bundles: masked autoencoding (MAE) and SimMIM. The alternative Swin-B backbone variants are out of scope for v0 (pending a 3D Swin-UNETR primitive).
+
+## Intended use
+
+As the MAE variant, but pretrained with the SimMIM masked-image-modelling objective (in-place masking + L1 reconstruction). Same encoder architecture and Triad-131K corpus; provided so downstream users can pick whichever SSL objective transfers better for their task. Encoder-only.
+
+## Usage
+
+```python
+from ilex.models.triad import TriadPlainConvUNet
+model = TriadPlainConvUNet.from_pretrained('ilex-hub/triad.plainconvunet-simmim.1')
+```
+
+## Authors
+
+Wang S., et al.
+
+## Citation
+
+Wang S., Safari M., Li Q., Chang C.-W., Qiu R. L. J., Roper J., Yu D. S., Yang X. (2025). Triad: Vision Foundation Model for 3D Magnetic Resonance Imaging. arXiv:2502.14064. The nnU-Net backbone the encoder is taken from: Isensee F., Jaeger P. F., Kohl S. A. A., Petersen J., Maier-Hein K. H. (2021). nnU-Net: a self- configuring method for deep learning-based biomedical image segmentation. Nature Methods 18(2):203-211. doi:10.1038/s41592-020-01008-z
+
+### References
+
+- Wang S., et al. (2025). Triad: Vision Foundation Model for 3D Magnetic Resonance Imaging. arXiv:2502.14064. https://arxiv.org/abs/2502.14064
+- Codebase: https://github.com/wangshansong1/Triad
+
+## License
+
+HF Hub license tag: `mit`
+
+**Effective terms:** MIT (Shansong Wang et al.) on both the Triad code (https://github.com/wangshansong1/Triad) and the released pretrained checkpoints. No commercial restrictions; no gating required. The arXiv preprint (2502.14064) is separately distributed under CC BY 4.0, but the code and weights the ilex bundle re-expresses are MIT. The ilex JAX / Equinox port code is separately licensed under Apache-2.0 / GPL-3.0; that does not alter the upstream MIT terms governing the weights.
+
+Upstream license reference: https://github.com/wangshansong1/Triad/blob/main/LICENSE
+
+### Copyright
+
+Network architecture and pretrained weights: copyright (c) the Triad authors, released under the MIT License. JAX / Equinox port: copyright (c) the ilex authors, released under the Apache-2.0 / GPL-3.0 dual license used by ilex itself.
+
+## Upstream source
+
+Original weights / reference implementation: https://github.com/wangshansong1/Triad
+
+## Provenance
+
+This artefact was produced by [ilex](https://github.com/hypercoil/ilex)'s
+save/load pipeline. The architecture is implemented in
+`ilex.models.triad.TriadPlainConvUNet` and the weights have been converted
+from their upstream format. See the upstream source above
+for the canonical reference.

config.json

@@ -0,0 +1,42 @@
+{
+  "_ilex": {
+    "architecture": "ilex.models.triad.model.TriadPlainConvUNet",
+    "constructor_kwargs": {
+      "input_channels": 1
+    },
+    "format": "ilex",
+    "framework_version": {
+      "equinox": "0.13.8",
+      "ilex": "0.0.0.dev0",
+      "jax": "0.10.0",
+      "jaxlib": "0.10.0",
+      "numpy": "2.4.4",
+      "safetensors": "0.7.0"
+    },
+    "has_state": false,
+    "origin": "ilex-native"
+  },
+  "authors": "Wang S., et al.",
+  "copyright": "Network architecture and pretrained weights: copyright (c) the Triad authors, released under the MIT License. JAX / Equinox port: copyright (c) the ilex authors, released under the Apache-2.0 / GPL-3.0 dual license used by ilex itself.",
+  "data_type": "nibabel",
+  "description": "Triad vision foundation model for 3D MRI, ported to JAX / Equinox from the upstream PyTorch release. Triad is an nnUNet PlainConvEncoder pretrained self-supervised on Triad-131K (131,170 3D MRI volumes spanning brain, breast, and prostate; T1/T2/FLAIR/DWI/fMRI/DCE) and serves as a transfer-learning backbone for downstream MRI segmentation, classification, and registration. The published checkpoints are encoder-only (the self-supervised decoder / mask token are stripped); this port exposes the pretrained encoder, whose multi-scale skip features are the transfer representation. Two pretraining objectives are released as separate bundles: masked autoencoding (MAE) and SimMIM. The alternative Swin-B backbone variants are out of scope for v0 (pending a 3D Swin-UNETR primitive).",
+  "equinox_version": "0.13.8",
+  "ilex_version": "0.0.0.dev0",
+  "image_classes": "Single-channel 3D MRI volume (contrast-general; pretrained across T1, T2, FLAIR, DWI, fMRI, DCE).",
+  "intended_use": "Research. A pretrained 3D-MRI encoder backbone for transfer learning; consumers attach a task-specific decoder / head and fine-tune. Inputs are single-channel 3D MRI volumes with each spatial dimension a multiple of 32.",
+  "jax_version": "0.10.0",
+  "label_classes": "N/A -- self-supervised backbone; no fixed label set. Output is the tuple of per-stage encoder feature maps.",
+  "network_data_format": {
+    "inputs": {},
+    "outputs": {}
+  },
+  "numpy_version": "2.4.4",
+  "pred_classes": "Multi-scale encoder skip features (6 stages, channels [32, 64, 128, 256, 320, 320]); the bottleneck is the deepest skip.",
+  "references": [
+    "Wang S., et al. (2025). Triad: Vision Foundation Model for 3D Magnetic Resonance Imaging. arXiv:2502.14064. https://arxiv.org/abs/2502.14064",
+    "Codebase: https://github.com/wangshansong1/Triad"
+  ],
+  "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20240725.json",
+  "task": "3D-MRI self-supervised foundation backbone (transfer learning)",
+  "version": "0.0.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dfa2c1bad59af37331957bf712c47871e25042becb0a1e4acd3b15d329ad498
+size 56105544