Skip to content
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

[Application] add README for LLaMA application @open sesame 11/07 16:01 #2787

Merged
merged 1 commit into from
Nov 8, 2024
Merged

[Application] add README for LLaMA application @open sesame 11/07 16:01 #2787

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
19 changes: 19 additions & 0 deletions Applications/LLaMA/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
# LLaMA

This application is an implementation of LLaMA.

It has been verified to run in Ubuntu and Android environments through meson build.

Reference:
- [Paper: The Llama 3 Herd of Models](https://arxiv.org/abs/2407.21783)

## How to run LLaMA

Please refer to the following documents for instructions on setting up and building NNTrainer.

- [Getting Started](../../docs/getting-started.md)
- [how-to-run-example-android](../../docs/how-to-run-example-android.md)

To run your own LLaMA model, you need to prepare three additional files inside the application build directory.
- For tokenizer usage, you will require a `vocab.json` file and a `merges.txt` file tailored to your specific model.
- To load pre-trained weights, ensure that you have a `.bin` file compatible with NNTrainer. You can convert your PyTorch model's weight file to NNTrainer model's weights file using the `Applications/LLaMA/PyTorch/weights_converter.py` script provided within our official repository.
Loading
Loading