Add EfficientSAM-Ti 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
+efficient-sam/efficient_sam_vitt_float32_static_p2.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,56 @@
+---
+license: apache-2.0
+base_model: yunyangx/EfficientSAM
+pipeline_tag: mask-generation
+library_name: coreai
+tags:
+  - coreai
+  - ios
+  - image-segmentation
+  - react-native
+---
+
+# EfficientSAM-Ti for Core AI
+
+[EfficientSAM](https://github.com/yformer/EfficientSAM) ViT-Tiny (10M parameters) 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 `ImageSegmenter` from the `CoreAISegmentation` product of `coreai-models`.
+
+It segments the object at a point (a click) or in a box, one mask per prompt.
+
+## Files
+
+`efficient-sam/` is a segmenter bundle: `metadata.json` and the exported model, float32, static shape, up to two points per prompt (39 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(
+  'segmentation',
+  { id: 'efficient-sam', sourceType: 'file', sourceUri: efficientSAMBundlePath },
+  { imageUri, data: { box: { x: 10, y: 50, width: 300, height: 400 } } },
+  {}
+)
+```
+
+In Swift:
+
+```swift
+let segmenter = try await ImageSegmenter(resourcesAt: "efficient-sam")
+let response = try await segmenter.segment(image: cgImage, pointQuery: query)
+```
+
+## Export
+
+From [`apple/coreai-models`](https://github.com/apple/coreai-models) at `09ff139`, with `coreai-core` 1.0.0b3:
+
+```bash
+cd models/efficient-sam
+uv run export.py
+```
+
+## License
+
+Apache-2.0, as the original model. EfficientSAM is by Y. Xiong et al., [EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything](https://arxiv.org/abs/2312.00863).

efficient-sam/efficient_sam_vitt_float32_static_p2.aimodel/main.hash

@@ -0,0 +1 @@
+�jN���&���v^?��S���"��a�

efficient-sam/efficient_sam_vitt_float32_static_p2.aimodel/main.mlirb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:986a1d4eafd8ed2696c4eaa0765e3ff513b31853a711d0efa9221e0682ad618a
+size 41062412

efficient-sam/efficient_sam_vitt_float32_static_p2.aimodel/metadata.json

@@ -0,0 +1,8 @@
+{
+  "creationDate" : "20261025T200920Z",
+  "assetVersion" : "2.0",
+  "description" : "EfficientSAM is a lightweight, promptable image segmentation model that uses a masked autoencoder pretrained ViT-Tiny encoder to reduce compute while preserving accuracy. Source: https:\/\/github.com\/yformer\/EfficientSAM",
+  "producer" : "coreai-core 1.0.0b3",
+  "author" : "Y. Xiong et al.",
+  "license" : "Apache-2.0"
+}

efficient-sam/metadata.json

@@ -0,0 +1,8 @@
+{
+  "metadata_version": "0.2",
+  "kind": "segmenter",
+  "name": "efficient_sam_vitt_float32_static_p2",
+  "assets": {
+    "main": "efficient_sam_vitt_float32_static_p2.aimodel"
+  }
+}