SLURM GPU Allocation

Question

I'm brand new to Linux / slurm / HPC so apologies if this seems trivial. I have access to a node, consisting of 4 GPUS, of a HPC. I have a job that when running on a single GPU runs out of memory so I want to throw the whole node at the job. The following SLURM submission allocates the GPUs to the job but the additional GPUs resources don't appear to be used when executing it.

#!/bin/bash

#SBATCH --job-name=JupTest
#SBATCH --gpus=4
#SBATCH --gpus-per-task=4
#SBATCH --time=02:30:00         # Hours:Mins:Secs
#SBATCH --output=/scratch/abc/pal.abc/jupyter_out.out

source ~/miniforge3/bin/activate Proj12
papermill "/home/abc/pal.abc/Jup.ipynb" -p file_path "/home/abc/pal.abc/Data.txt" -p file_prefix Output -p nom_file "/home/abc/pal.abc/Nom.txt" -

How do I go about submitting the job so that all the node resources are used to do a single run of the jupyter notebook?