Upload folder using huggingface_hub

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+library_name: pytorch
+pipeline_tag: image-classification
+tags:
+- robotics
+- egocentric-video
+- capture-qa
+- hand-detection
+- edge
+- tinyml
+datasets:
+- lerobot/droid_1.0.1
+- imageomics/KABR
+model-index:
+- name: referee-hands-s
+  results:
+  - task:
+      type: image-classification
+      name: Hand/gripper visibility (clip-level)
+    dataset:
+      type: referee-lab/hands-visible
+      name: referee-lab/hands-visible (Prime Intellect Environments Hub)
+      split: full
+    metrics:
+    - type: accuracy
+      name: Clip accuracy
+      value: 0.9778
+---
+
+# referee-hands-s
+
+A **1.5M-parameter** MobileNetV3-small that answers one question about robot-training
+video: *is a hand or gripper visible?* Distilled from gemma3:27b pseudo-labels
+(4,138 frames from DROID / ALOHA-sim / KABR — all CC BY / CC0 / MIT), 96px inputs,
+built to fit a microcontroller inference budget.
+
+## Scoreboard (public benchmark: [referee-lab/hands-visible](https://github.com/publu/referee-lab))
+
+| Model | Params | Accuracy |
+|---|---|---|
+| gemma3:27b (the teacher) | 27B | 97.8% |
+| **referee-hands-s (this model)** | **1.5M** | **97.8%** |
+| qwen2.5vl:32b | 32B | 74.4% |
+| *do-nothing floor (constant "yes")* | — | *68.9%* |
+| qwen2.5vl:7b | 7B | 45.6% |
+| EgoSieve-S (hand-visibility head) | 22M | 40.0% |
+| MediaPipe HandLandmarker | — | 40.0% |
+
+Scored on the public 45-clip answer sheet, clip verdict = any frame above 0.5.
+**Caveat, stated plainly:** training frames come from different clips but the same
+source videos as the benchmark — an in-domain result. A cross-video split is the
+planned follow-up. The benchmark's own labels are machine-graded provisional with a
+published grading record.
+
+## Usage
+
+```python
+import torch
+from torchvision import models, transforms
+from safetensors.torch import load_file
+
+net = models.mobilenet_v3_small()
+net.classifier[3] = torch.nn.Linear(net.classifier[3].in_features, 1)
+net.load_state_dict(load_file("model.safetensors"))
+net.eval()
+
+tf = transforms.Compose([transforms.Resize((96, 96)), transforms.ToTensor()])
+p = torch.sigmoid(net(tf(img).unsqueeze(0)).squeeze())   # P(hand/gripper visible)
+```
+
+Clip-level: sample ~12 frames, answer yes if `max(p) > 0.5`.
+
+## Provenance
+
+Teacher: gemma3:27b (96.7-97.8% on the same benchmark). Training/eval media:
+DROID (CC BY 4.0), lerobot aloha sim (MIT), KABR (CC0). The benchmark, its
+validation gates, and all baseline runs: https://github.com/publu/referee-lab —
+five capture-QA evals, publicly runnable on the Prime Intellect Environments Hub
+(`prime eval run referee-lab/hands-visible`).

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b793f7a6d252d5e81928c7f3ee7c9d168f7feea1b6267c556ea8b7e0951ee90d
+size 6147500