Apply the model card standard

README.md

@@ -4,40 +4,52 @@ pipeline_tag: image-to-image
 library_name: executorch
 ---
 
-# Introduction
+# style-transfer-candy
 
-This repository hosts the [style
-transfer](https://github.com/pytorch/examples/tree/main/fast_neural_style) candy
-models for the [React Native
-ExecuTorch](https://www.npmjs.com/package/react-native-executorch) library. It
-includes model exported for xnnpack, as well as coreml in `.pte` format, ready
-for use in the **ExecuTorch** runtime.
+This repository hosts the **style-transfer-candy** 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.
 
-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.
+Upstream model: [style transfer](https://github.com/pytorch/examples/tree/main/fast_neural_style)
 
-## Compatibility
+## Variants
+
+| Path | Backend | Precision |
+| --- | --- | --- |
+| `coreml/style_transfer_candy_coreml_fp16.pte` | coreml | fp16 |
+| `xnnpack/style_transfer_candy_xnnpack_fp32.pte` | xnnpack | fp32 |
+| `xnnpack/style_transfer_candy_xnnpack_int8.pte` | xnnpack | int8 |
+
+## Unshipped backends
 
-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 from the library will
-guarantee compatibility with runtime used behind the scenes.
+A backend directory carrying a `NOTES.md` and no `.pte` was exported and
+not published. Its note records what went wrong.
 
-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.
+- `mlx` ([why](https://huggingface.co/software-mansion/react-native-executorch-style-transfer-candy/blob/main/mlx/NOTES.md))
 
-### Repository Structure
+## Repository structure
 
-The repository is organized into two main directories:
+```
+LICENSE                                        3.4 kB
+config.json                                    42 B
+coreml/config.json                             889 B
+coreml/style_transfer_candy_coreml_fp16.pte    3.6 MB
+mlx/NOTES.md                                   2.6 kB
+xnnpack/config.json                            1.4 kB
+xnnpack/style_transfer_candy_xnnpack_fp32.pte  6.5 MB
+xnnpack/style_transfer_candy_xnnpack_int8.pte  1.8 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 differentely exported version of the model.
+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.