bhanc commited on
Commit
cb3d5d5
·
1 Parent(s): 9a88de9

Update README

Browse files
Files changed (1) hide show
  1. README.md +25 -6
README.md CHANGED
@@ -4,18 +4,37 @@ license: mit
4
 
5
  # Introduction
6
 
7
- This repository hosts the image encoder of [clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) 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.
 
 
 
 
 
8
 
9
- 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.
 
 
10
 
11
  ## Compatibility
12
 
13
- 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 runtime used behind the scenes.
 
 
 
 
 
 
14
 
15
- These models were exported using `v0.6.0` version and **no forward compatibility** is guaranteed. Older versions of the runtime may not work with these files.
 
 
16
 
17
  ### Repository Structure
18
 
19
- All files are located in the root directory.
20
 
21
- - The `.pte` file should be as the `modelSource` argument.
 
 
 
 
 
4
 
5
  # Introduction
6
 
7
+ This repository hosts the image encoder of
8
+ [clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32)
9
+ model for the [React Native
10
+ ExecuTorch](https://www.npmjs.com/package/react-native-executorch) library. It
11
+ includes the model exported for xnnpack in `.pte` format, ready for use in the
12
+ **ExecuTorch** runtime.
13
 
14
+ If you'd like to run these models in your own ExecuTorch runtime, refer to the
15
+ [official documentation](https://pytorch.org/executorch/stable/index.html) for
16
+ setup instructions.
17
 
18
  ## Compatibility
19
 
20
+ If you intend to use this model outside of React Native ExecuTorch, make sure
21
+ your runtime is compatible with the **ExecuTorch** version used to export the
22
+ `.pte` files. For more details, see the compatibility note in the [ExecuTorch
23
+ GitHub
24
+ repository](https://github.com/pytorch/executorch/blob/11d1742fdeddcf05bc30a6cfac321d2a2e3b6768/runtime/COMPATIBILITY.md?plain=1#L4).
25
+ If you work with React Native ExecuTorch, the constants from the library will
26
+ guarantee compatibility with runtime used behind the scenes.
27
 
28
+ These models were exported using **ExecuTorch** version 1.1.0 and **no forward
29
+ compatibility** is guaranteed. Older versions of the runtime may not work with
30
+ these files.
31
 
32
  ### Repository Structure
33
 
34
+ The repository is organized directories:
35
 
36
+ - `xnnpack`
37
+
38
+ Each directory contains models exported for the respective backend.
39
+
40
+ - The `.pte` file should be passed to the `modelSource` parameter.