boehmchen / xLLaMa

xLLaMa

Setup

1. Install Docker

See Docker Installation (if not already installed)

2. Install Python 3

Install at least Python 3.10 with Pip (if not already installed). Earlier versions might work but are not tested.

3. Clone this Repository

git clone https://github.com/CR1337/xLLaMa.git

4. Change into the Repository

cd xLLaMa

5. Create a virtual environment (optional)

python3 -m venv .venv

6. Activate the virtual environment (optional)

source .venv/bin/activate

7. Run setup script

If you are on the production server with GPUs 2 and 3, run

bin/setup

else run

bin/setup-local

Usage

1. Run the application

For running in the background (recommended for production):

bin/run

For seeing terminal output (recommended for development):

bin/run-blocking

If you are not on the production server with GPUs 2 and 3 use

bin/run-local

or

bin/run-blocking-local

respectively.

2. Open the application

Open the application in a browser at http://localhost:8080. You can replace localhost with the IP of the server.

3. Stop the application

bin/stop

or if you are not on the production server with GPUs 2 and 3

bin/stop-local