Apply the model card standard

README.md

@@ -3,40 +3,50 @@ license: bsd-3-clause
 pipeline_tag: object-detection
 library_name: executorch
 ---
-# Introduction
 
-This repository hosts the [SSDLite320 MobilenetV3
-Large](https://pytorch.org/vision/main/models/generated/torchvision.models.detection.ssdlite320_mobilenet_v3_large.html#ssdlite320-mobilenet-v3-large)
-model for the [React Native
-ExecuTorch](https://www.npmjs.com/package/react-native-executorch) library. It
-includes the model exported for xnnpack in `.pte` format, ready for use in the
-**ExecuTorch** runtime.
+# ssdlite320-mobilenet-v3-large
 
-If you'd like to run these models in your own ExecuTorch runtime, refer to the
-[official documentation](https://pytorch.org/executorch/stable/index.html) for
-setup instructions.
+This repository hosts the **ssdlite320-mobilenet-v3-large** models exported for the
+[React Native ExecuTorch](https://www.npmjs.com/package/react-native-executorch)
+library as ExecuTorch `.pte` programs, ready to run on device.
 
-## Compatibility
+Upstream model: [SSDLite320 MobilenetV3 Large](https://pytorch.org/vision/main/models/generated/torchvision.models.detection.ssdlite320_mobilenet_v3_large.html#ssdlite320-mobilenet-v3-large)
+
+## Variants
+
+| Path | Backend | Precision |
+| --- | --- | --- |
+| `coreml/ssdlite320_mobilenet_v3_large_coreml_fp16.pte` | coreml | fp16 |
+| `xnnpack/ssdlite320_mobilenet_v3_large_xnnpack_fp32.pte` | xnnpack | fp32 |
 
-If you intend to use this models outside of React Native ExecuTorch, make sure
-your runtime is compatible with the **ExecuTorch** version used to export the
-`.pte` files. For more details, see the compatibility note in the [ExecuTorch
-GitHub
-repository](https://github.com/pytorch/executorch/blob/11d1742fdeddcf05bc30a6cfac321d2a2e3b6768/runtime/COMPATIBILITY.md?plain=1#L4).
-If you work with React Native ExecuTorch, the constants shipped with the library
-will guarantee compatibility with runtime used behind the scenes.
+## Unshipped backends
 
-These models were exported using **ExecuTorch** version 1.1.0 and **no forward
-compatibility** is guaranteed. Older versions of the runtime may not work with
-these files.
+A backend directory carrying a `NOTES.md` and no `.pte` was exported and
+not published. Its note records what went wrong.
 
-### Repository Structure
+- `mlx` ([why](https://huggingface.co/software-mansion/react-native-executorch-ssdlite320-mobilenet-v3-large/blob/main/mlx/NOTES.md))
 
-The repository is organized into two main directories:
+## Repository structure
+
+```
+config.json                                             51 B
+coreml/config.json                                      1.1 kB
+coreml/ssdlite320_mobilenet_v3_large_coreml_fp16.pte    8.1 MB
+mlx/NOTES.md                                            3.4 kB
+xnnpack/config.json                                     1.1 kB
+xnnpack/ssdlite320_mobilenet_v3_large_xnnpack_fp32.pte  13.3 MB
+```
+
+## Compatibility
 
-- `xnnpack`
-- `coreml`
+These files are published for the **ExecuTorch v1.4.1** runtime. ExecuTorch
+gives no forward compatibility guarantee, so an older runtime may fail to load
+them.
 
-Each directory contains models exported for the respective backend.
+To use them in React Native ExecuTorch, pass the model constant shipped in the
+library's model registry to the corresponding task pipeline. See the
+[documentation](https://docs.swmansion.com/react-native-executorch/docs/fundamentals/loading-models).
 
-- The `.pte` file should be passed to the `modelSource` parameter.
+To load these files in your own ExecuTorch runtime, read the
+[compatibility note](https://github.com/pytorch/executorch/blob/main/runtime/COMPATIBILITY.md)
+first.