Apply the model card standard

README.md

@@ -4,32 +4,57 @@ pipeline_tag: image-segmentation
 library_name: executorch
 ---
 
-# Introduction
+# fast-sam
 
-This repository hosts the instance segmentation
-[FastSAM](https://docs.ultralytics.com/models/fast-sam/) models
-for the [React Native
-ExecuTorch](https://www.npmjs.com/package/react-native-executorch) library. It
-includes models exported for xnnpack in `.pte` format, ready for use in the
-**ExecuTorch** runtime.
+This repository hosts the **fast-sam** 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: [FastSAM](https://docs.ultralytics.com/models/fast-sam/)
 
-# Compatibility
+## Variants
 
-If you intend to use these 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. If you work with React Native ExecuTorch, the constants from the
-library will guarantee compatibility with runtime used behind the scenes.
+| Path | Backend | Precision |
+| --- | --- | --- |
+| `s/coreml/fast_sam_s_coreml_fp16.pte` | coreml | fp16 |
+| `s/xnnpack/fast_sam_s_xnnpack_fp32.pte` | xnnpack | fp32 |
+| `x/coreml/fast_sam_x_coreml_fp16.pte` | coreml | fp16 |
+| `x/xnnpack/fast_sam_x_xnnpack_fp32.pte` | xnnpack | fp32 |
 
-These models were exported using **ExecuTorch** version 1.2.0 and no forward
-compatibility is guaranteed. Older versions of the runtime may not work with
-these files.
+## Unshipped backends
 
+A backend directory carrying a `NOTES.md` and no `.pte` was exported and
+not published. Its note records what went wrong.
 
-# Licencing 
+- `s/mlx` ([why](https://huggingface.co/software-mansion/react-native-executorch-fast-sam/blob/main/s/mlx/NOTES.md))
+- `x/mlx` ([why](https://huggingface.co/software-mansion/react-native-executorch-fast-sam/blob/main/x/mlx/NOTES.md))
 
-Please note that Ultralytics shares YOLO under the AGPL-3.0 license. Due to the copyleft nature of this license, the models provided in this repository are also distributed under the terms of the AGPL-3.0.
+## Repository structure
+
+```
+config.json                            30 B
+s/coreml/config.json                   1.2 kB
+s/coreml/fast_sam_s_coreml_fp16.pte    23.1 MB
+s/mlx/NOTES.md                         2.0 kB
+s/xnnpack/config.json                  1.2 kB
+s/xnnpack/fast_sam_s_xnnpack_fp32.pte  45.2 MB
+x/coreml/config.json                   1.2 kB
+x/coreml/fast_sam_x_coreml_fp16.pte    139 MB
+x/mlx/NOTES.md                         2.0 kB
+x/xnnpack/config.json                  1.2 kB
+x/xnnpack/fast_sam_x_xnnpack_fp32.pte  276 MB
+```
+
+## Compatibility
+
+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.
+
+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).
+
+To load these files in your own ExecuTorch runtime, read the
+[compatibility note](https://github.com/pytorch/executorch/blob/main/runtime/COMPATIBILITY.md)
+first.