Add YOLOS-tiny exported with apple/coreai-models

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+yolos-tiny.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+base_model: hustvl/yolos-tiny
+pipeline_tag: object-detection
+library_name: coreai
+tags:
+  - coreai
+  - ios
+  - object-detection
+  - react-native
+---
+
+# YOLOS-tiny for Core AI
+
+[hustvl/yolos-tiny](https://huggingface.co/hustvl/yolos-tiny) (6.5M parameters, COCO classes) exported to Apple Core AI, unmodified, with the [`apple/coreai-models`](https://github.com/apple/coreai-models) recipe. It runs on iOS 27 and macOS 27 with the `ObjectDetector` from the `CoreAIObjectDetection` product of `coreai-models`.
+
+## Files
+
+`yolos-tiny.aimodel/` is the exported model, float32, static shape (23 MB).
+
+## Use
+
+With [`@react-native-ai/core-ai`](https://github.com/callstackincubator/ai), download the folder and pass its path:
+
+```typescript
+import { CoreAI } from '@react-native-ai/core-ai'
+
+const result = await CoreAI.runTask(
+  'object-detection',
+  { id: 'yolos-tiny', sourceType: 'file', sourceUri: yolosModelPath },
+  { imageUri },
+  { threshold: 0.7 }
+)
+```
+
+In Swift:
+
+```swift
+let detector = try await ObjectDetector(resourcesAt: "yolos-tiny.aimodel")
+let detections = try await detector.detect(image: cgImage)
+```
+
+## Export
+
+From [`apple/coreai-models`](https://github.com/apple/coreai-models) at `09ff139`, with `coreai-core` 1.0.0b3:
+
+```bash
+cd models/yolo
+uv run export.py --model hustvl/yolos-tiny
+```
+
+## License
+
+Apache-2.0, as the original model. YOLOS is by Y. Fang et al., [You Only Look at One Sequence](https://arxiv.org/abs/2106.00666).

yolos-tiny.aimodel/main.mlirb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f8c40b24807815119cf89e695e91f82e80d8ca2027349e55b68313f3998f00
+size 23616392

yolos-tiny.aimodel/metadata.json

@@ -0,0 +1,8 @@
+{
+  "producer" : "coreai-core 1.0.0b3",
+  "author" : "Y. Fang et al.",
+  "assetVersion" : "2.0",
+  "creationDate" : "20261025T200808Z",
+  "description" : "YOLOS (You Only Look at One Sequence) applies a plain Vision Transformer directly to image patches and predicts object queries as bounding boxes and class logits. Source: https:\/\/huggingface.co\/hustvl\/yolos-tiny",
+  "license" : "Apache-2.0"
+}