Correct the license and the upstream projects in the card

The card said MIT and named openvinotoolkit/anomalib as the project that was converted. The conversion uses the weights of MSherbinii/efficientad-bottle, which are MIT. The anomaly map computation in the model is adapted from nelson1425/EfficientAD, which is under the Apache License 2.0. The conversion does not use anomalib. The card now names both projects with their licenses.

The card also said that the Models Zoo app runs this model. The app's catalog does not list it, so that line is removed.

The model files are unchanged.

README.md

@@ -1,5 +1,7 @@
 ---
-license: mit
+license: other
+license_name: apache-2.0-and-mit
+license_link: https://huggingface.co/mlboydaisuke/EfficientAD-CoreML#license
 library_name: coreml
 pipeline_tag: image-segmentation
 tags:
@@ -24,12 +26,12 @@ Visual anomaly detection for industrial inspection. Outputs a per-pixel anomaly
 
 PDN-Small teacher/student pair plus an autoencoder: the anomaly map is the disagreement between teacher-student and autoencoder-student. This checkpoint is trained on the MVTec AD *bottle* category — retrain per category for other objects.
 
-Core ML conversion of [openvinotoolkit/anomalib](https://github.com/openvinotoolkit/anomalib) for on-device inference on iPhone, iPad and Mac. Converted with `coremltools`; the packages are stateless, so all sequencing and buffering lives in your Swift code.
+Core ML conversion of the EfficientAD weights [MSherbinii/efficientad-bottle](https://huggingface.co/MSherbinii/efficientad-bottle) for on-device inference on iPhone, iPad and Mac. The anomaly map computation is adapted from [nelson1425/EfficientAD](https://github.com/nelson1425/EfficientAD). Converted with `coremltools`; the packages are stateless, so all sequencing and buffering lives in your Swift code.
 
 | | |
 |---|---|
 | Task | image segmentation |
-| Upstream | [openvinotoolkit/anomalib](https://github.com/openvinotoolkit/anomalib) |
+| Upstream | [nelson1425/EfficientAD](https://github.com/nelson1425/EfficientAD) (code), [MSherbinii/efficientad-bottle](https://huggingface.co/MSherbinii/efficientad-bottle) (weights) |
 | Packages | 1 |
 | Download size | 14 MB |
 | Minimum iOS | 17.0 |
@@ -70,7 +72,6 @@ let model = try MLModel(contentsOf: compiled, configuration: config)
 ## Demo
 
 - **Sample app** — [`sample_apps/EfficientADDemo`](https://github.com/john-rocky/CoreML-Models/tree/master/sample_apps/EfficientADDemo), a standalone SwiftUI project.
-- **Models Zoo** — this model is downloadable and runnable inside the [Models Zoo app](https://apps.apple.com/app/id6762083207) on the App Store, no build required.
 
 ## Conversion
 
@@ -80,11 +81,12 @@ let model = try MLModel(contentsOf: compiled, configuration: config)
 
 ## License
 
-The conversion inherits the upstream license: **MIT**.
+- Weights: [MSherbinii/efficientad-bottle](https://huggingface.co/MSherbinii/efficientad-bottle), MIT License.
+- Code: the anomaly map computation in the model is adapted from [nelson1425/EfficientAD](https://github.com/nelson1425/EfficientAD), Apache License 2.0.
 
 ## Credits
 
-- Upstream authors: [openvinotoolkit/anomalib](https://github.com/openvinotoolkit/anomalib), 2023
+- Upstream authors: [nelson1425/EfficientAD](https://github.com/nelson1425/EfficientAD) (code, 2023) and [MSherbinii/efficientad-bottle](https://huggingface.co/MSherbinii/efficientad-bottle) (weights)
 - Core ML conversion: john-rocky (Daisuke Majima)
 
 <!-- funnel:v1 -->