Upload folder using huggingface_hub

LICENSE

@@ -0,0 +1,15 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+library_name: transformers
+base_model: []
+tags:
+  - gaze-estimation
+  - gaze-target-estimation
+  - dinov3
+pipeline_tag: image-feature-extraction
+---
+
+# PaGE-ViT-B
+
+Base variant, general scenes. Distilled. Part of the [PaGE](https://huggingface.co/Octopus1/PaGE) gaze target estimation family.
+
+- **Backbone:** DINOv3 ViT-B/16
+- **Params:** ~90M
+- **Scene input:** 512×512, **Head input:** 256×256, **Heatmap output:** 64×64
+- **Source checkpoint:** `vitb_distill.pt`
+
+## Self-contained weights
+
+This checkpoint includes the full DINOv3 backbone weights in its `safetensors` files. **No external
+DINOv3 weights are downloaded.** The model code (`modeling_page.py`) is loaded automatically from
+[`Octopus1/PaGE`](https://huggingface.co/Octopus1/PaGE) via `auto_map` when you pass `trust_remote_code=True`.
+
+## Installation
+
+```bash
+pip install torch torchvision timm "transformers>=4.56" safetensors pillow
+```
+
+## Usage
+
+```python
+from transformers import AutoModel, AutoImageProcessor
+from PIL import Image
+import torch
+
+repo = "Octopus1/page-vitb"
+model = AutoModel.from_pretrained(repo, trust_remote_code=True).eval()
+processor = AutoImageProcessor.from_pretrained(repo, trust_remote_code=True)
+
+scene = Image.open("scene.jpg").convert("RGB")
+head = Image.open("head.jpg").convert("RGB")
+
+inputs = processor(scene, head_crops=[head], bboxes=[[(0.10, 0.10, 0.30, 0.40)]])
+
+with torch.no_grad():
+    out = model(inputs)
+
+heatmap = out["heatmap"][0]   # [Np, 64, 64]
+inout   = out["inout"][0]     # [Np]
+```
+
+## Inputs / Outputs
+
+See the family [README](https://huggingface.co/Octopus1/PaGE) for the full input/output spec.
+
+- Input dict: `images` (list of `[B,3,512,512]`), `head_images` (list of `[sum(Np),3,256,256]`),
+  `bboxes` (per-image list of `(xmin,ymin,xmax,ymax)` in `[0,1]`).
+- Output dict: `heatmap` (list of `[Np,64,64]`, sigmoid), `inout` (list of `[Np]`, sigmoid).
+
+## License
+
+Apache-2.0.

config.json

@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "PaGEModel"
+  ],
+  "dim": 256,
+  "dino_feature_dropout": 0.1,
+  "dinov3_drop_path_rate": 0.0,
+  "dinov3_hidden_size": 768,
+  "dinov3_intermediate_size": 3072,
+  "dinov3_layer_norm_eps": 1e-05,
+  "dinov3_layerscale_value": 1.0,
+  "dinov3_num_attention_heads": 12,
+  "dinov3_num_hidden_layers": 12,
+  "dinov3_num_register_tokens": 4,
+  "dinov3_patch_size": 16,
+  "dinov3_use_gated_mlp": false,
+  "drop_path": 0.1,
+  "dtype": "float32",
+  "head_in_size": [
+    256,
+    256
+  ],
+  "heatmap_out_size": [
+    64,
+    64
+  ],
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "inout": true,
+  "mlp_layer": "geglu",
+  "mlp_ratio": 4.0,
+  "model_type": "page",
+  "n_head_self_attn_layers": 1,
+  "n_reg_tokens": 4,
+  "n_scene_head_interaction_layers": 5,
+  "n_scene_self_attn_layers": 1,
+  "num_heads": 8,
+  "pos_encoding": "rope",
+  "scene_in_size": [
+    512,
+    512
+  ],
+  "transformers_version": "4.56.0",
+  "use_head_prompt": false,
+  "auto_map": {
+    "AutoConfig": "Octopus1/PaGE--modeling_page.PaGEConfig",
+    "AutoModel": "Octopus1/PaGE--modeling_page.PaGEModel"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd03a4e5807c188903f00056113b668a0980d4fd992db336eac9c766b93e0617
+size 749309236

preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "image_processor_type": "PaGEImageProcessor",
+  "auto_map": {
+    "AutoImageProcessor": "Octopus1/PaGE--modeling_page.PaGEImageProcessor"
+  },
+  "scene_size": [
+    512,
+    512
+  ],
+  "head_size": [
+    256,
+    256
+  ],
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2
+}