Skip to content

Update iOS.md #439

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Apr 24, 2024
Merged

Update iOS.md #439

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6ea76e5
Update iOS.md
shoumikhin Apr 24, 2024
1a56df0
Update iOS.md
shoumikhin Apr 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 23 additions & 10 deletions docs/iOS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,19 +3,32 @@
Check out the [tutorial](https://pytorch.org/executorch/main/llm/llama-demo-ios.html) on how to build the iOS demo app running your
PyTorch models with [ExecuTorch](https://github.com/pytorch/executorch).

Once you can run the app on you device,
1 - connect the device to you Mac,
2 - copy the model and tokenizer.bin to the iOS Llama app
3 - select the tokenizer and model with the `(...)` control (bottom left of screen, to the left of the text entrybox)
```
git clone https://github.com/pytorch/executorch.git
cd executorch
Detailed step by step in conjunction with ExecuTorch iOS build, to run on
simulator for iOS.
git submodule update --init
open examples/demo-apps/apple_ios/LLaMA/LLaMA.xcodeproj
```

Then click the Play button in Xcode to launch the app in Simulator.

To run on a device, given that you already have it set up for development, you'll need to have a provisioning profile with the [`increased-memory-limit`](https://developer.apple.com/documentation/bundleresources/entitlements/com_apple_developer_kernel_increased-memory-limit) entitlement. Just change the app's bundle identifier to whatever matches your provisioning profile with the aforementioned capability enabled.

After the app launched successfully, copy an exported ExecuTorch model (`.pte`) and tokenizer (`.bin`) files to the iLLaMA folder.

For the Simulator, just drap&drop both files onto the Simulator window and save at `On My iPhone > iLLaMA` folder.

For a device, open it in a separate Finder window, navigate to the Files tab, drag&drop both files to the iLLaMA folder and wait till the copying finishes.

Now, follow the app's UI guidelines to pick the model and tokenizer files from the local filesystem and issue a prompt.

Feel free to reuse the [`LLaMARunner`](https://github.com/pytorch/executorch/tree/main/examples/demo-apps/apple_ios/LLaMA/LLaMARunner/LLaMARunner/Exported) component from the demo app with its C++ [dependencies](https://github.com/pytorch/executorch/tree/main/examples/models/llama2) to your project and give it a spin.

Click the image below to see it in action!

<a href="https://pytorch.org/executorch/main/_static/img/llama_ios_app.mp4">
<img src="https://pytorch.org/executorch/main/_static/img/llama_ios_app.png" width="600" alt="iOS app running a LlaMA model">
</a>

<--
<A HREF=https://github.com/pytorch/executorch/blob/main/docs/source/_static/img/llama_ios_app.png>torchchat on iOS</A>
-->