Add direct timm loading

README.md

@@ -1,38 +1,67 @@
 ---
 license: mit
+library_name: timm
 pipeline_tag: image-classification
 tags:
 - image-classification
 - vision-transformer
+- adaptive-inference
 - imagenet-1k
 - progresvit
+- arxiv:2609.03216
 datasets:
 - ILSVRC/imagenet-1k
+metrics:
+- accuracy
 ---
 
 # ProgResViT DeiT-S (192 → 240)
 
-EMA inference checkpoint for the DeiT-S ProgResViT model trained on ImageNet-1K.
+ImageNet-1K EMA weights for **ProgResViT DeiT-S (192 → 240)** from [ProgResViT: Progressive Resolution and Width for Adaptive Vision Transformers](https://arxiv.org/abs/2609.03216).
 
-- Paper: [ProgResViT: Progressive Resolution and Width for Adaptive Vision Transformers](https://huggingface.co/papers/2609.03216)
+- Paper: [arXiv:2609.03216](https://arxiv.org/abs/2609.03216)
+- Hugging Face paper: [2609.03216](https://huggingface.co/papers/2609.03216)
 - Code: [ds-kiel/ProgResViT](https://github.com/ds-kiel/ProgResViT)
-
 - Training: standard
-- Paper-reported full-path top-1 accuracy: 82.206%
+- Full-path top-1 accuracy: 82.206%
 - Full-path compute: 6.267 GMACs
 
-## Download
+## Usage
+
+Run from the cloned ProgResViT repository root, or add the repository to `PYTHONPATH`:
+
+```python
+import torch
+from timm.models import create_model
+
+model = create_model("hf-hub:NCPS/progresvit-deit-s-192-240-imagenet1k", pretrained=True)
+model.eval()
+
+x = torch.randn(1, 3, 240, 240)
+with torch.inference_mode():
+    logits, stage = model(x, threshold=0.35)
+
+print(logits.shape)  # (1, 1000)
+print(stage)         # 0 = 192 px / 3 heads; 1 = 240 px / 6 heads
+```
+
+The entropy threshold controls routing. Lower values send more images to the second round; higher values exit more images after the first round.
+
+## ImageNet-1K validation
+
+Download the release checkpoint into `checkpoints/`:
 
 ```python
 from huggingface_hub import hf_hub_download
 
-checkpoint = hf_hub_download(
+hf_hub_download(
     repo_id="NCPS/progresvit-deit-s-192-240-imagenet1k",
     filename="progresvit_192_240.pth.tar",
+    local_dir="checkpoints",
 )
 ```
 
-The file contains EMA weights and public architecture metadata only. Run validation from the cloned ProgResViT repository:
+Then run the repository evaluator:
 
 ```bash
 python validate.py /path/to/imagenet/val \

config.json

@@ -0,0 +1,43 @@
+{
+  "architecture": "progresvit",
+  "num_classes": 1000,
+  "num_features": 384,
+  "global_pool": "token",
+  "model_args": {
+    "img_size": 240,
+    "progress_stages": [
+      3,
+      6
+    ],
+    "progress_img_sizes": [
+      192,
+      240
+    ]
+  },
+  "pretrained_cfg": {
+    "custom_load": false,
+    "input_size": [
+      3,
+      240,
+      240
+    ],
+    "fixed_input_size": true,
+    "interpolation": "bicubic",
+    "crop_pct": 0.9,
+    "crop_mode": "center",
+    "mean": [
+      0.485,
+      0.456,
+      0.406
+    ],
+    "std": [
+      0.229,
+      0.224,
+      0.225
+    ],
+    "num_classes": 1000,
+    "pool_size": null,
+    "first_conv": "patch_embed.proj",
+    "classifier": "head"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac2424b4075474c62e814fecf32c571b86636721df59bdf1a24fd2631c9cfa7e
+size 98958112