Apply the model card standard

README.md

@@ -9,18 +9,42 @@ pipeline_tag: token-classification
 library_name: executorch
 ---
 
-# Introduction
+# privacy-filter-openai
 
-This repository hosts the **OpenAI/privacy-filter** model for the [React Native ExecuTorch](https://www.npmjs.com/package/react-native-executorch) library. It includes a **quantized** version in `.pte` format, ready for use in the **ExecuTorch** runtime.
+This repository hosts the **privacy-filter-openai** 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.
+## Variants
+
+| Path | Backend | Precision |
+| --- | --- | --- |
+| `mlx/privacy_filter_openai_mlx_int4.pte` | mlx | int4 |
+| `xnnpack/privacy_filter_openai_xnnpack_8da4w.pte` | xnnpack | 8da4w |
+
+## Repository structure
+
+```
+config.json                                      43 B
+mlx/config.json                                  962 B
+mlx/privacy_filter_openai_mlx_int4.pte           835 MB
+tokenizer.json                                   26.6 MB
+tokenizer_config.json                            234 B
+viterbi_calibration.json                         372 B
+xnnpack/config.json                              972 B
+xnnpack/privacy_filter_openai_xnnpack_8da4w.pte  1.2 GB
+```
 
 ## Compatibility
 
-If you intend to use this model 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 the runtime used behind the scenes.
+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.
 
-## Repository Structure
+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 repository is organized as follows:
-- The `.pte` file should be passed to the `modelSource` parameter.
-- The tokenizer files are available in the repo root: `tokenizer.json` and `tokenizer_config.json` should be passed to `tokenizerSource` and `tokenizerConfigSource` respectively.
+To load these files in your own ExecuTorch runtime, read the
+[compatibility note](https://github.com/pytorch/executorch/blob/main/runtime/COMPATIBILITY.md)
+first.