1 files changed, 48 insertions, 0 deletions
diff --git a/collaborativeagents/slurm/test_70b_pilot.sh b/collaborativeagents/slurm/test_70b_pilot.sh
new file mode 100755
index 0000000..3514e86
--- /dev/null
+++ b/collaborativeagents/slurm/test_70b_pilot.sh
@@ -0,0 +1,48 @@
+#!/bin/bash
+#SBATCH --job-name=test_70b
+#SBATCH --account=bfqt-delta-gpu
+#SBATCH --partition=gpuA100x4
+#SBATCH --nodes=1
+#SBATCH --ntasks=1
+#SBATCH --cpus-per-task=16
+#SBATCH --gres=gpu:nvidia_a100:4
+#SBATCH --mem=200G
+#SBATCH --time=01:00:00
+#SBATCH --output=logs/test_70b_%j.out
+#SBATCH --error=logs/test_70b_%j.err
+
+# Pilot test for 70B AWQ user model
+# Tests that the model loads without OOM and multi-turn works
+
+set -e
+
+cd /projects/bfqt/users/yurenh2/ml-projects/personalization-user-model
+
+# Create logs directory
+mkdir -p collaborativeagents/slurm/logs
+
+echo "Starting 70B pilot test at $(date)"
+echo "Job ID: $SLURM_JOB_ID"
+echo "Node: $SLURMD_NODENAME"
+echo "GPUs: $CUDA_VISIBLE_DEVICES"
+
+# Activate environment
+source /u/yurenh2/miniforge3/etc/profile.d/conda.sh
+conda activate eval
+
+# Check GPU availability
+nvidia-smi
+
+# Set HF cache to project space
+export HF_HOME=/projects/bfqt/users/yurenh2/hf_cache/huggingface
+mkdir -p $HF_HOME
+
+# Add project to path
+export PYTHONPATH="${PWD}/src:${PWD}/collaborativeagents:${PYTHONPATH}"
+
+# Run pilot test
+cd collaborativeagents/scripts
+echo "Running 70B pilot test..."
+python test_70b_pilot.py
+
+echo "Pilot test completed at $(date)"