Files
Project_Velocity/infrastructure/desineuron_ingress/acquire_qwen35_122b_nvfp4.sh
2026-04-23 01:20:21 +05:30

21 lines
756 B
Bash

#!/usr/bin/env bash
set -euo pipefail
TARGET_PATH="${TARGET_PATH:-/opt/dlami/nvme/models/cyankiwi-Qwen3.5-122B-A10B-AWQ-4bit}"
MODEL_REPO="${MODEL_REPO:-cyankiwi/Qwen3.5-122B-A10B-AWQ-4bit}"
mkdir -p "${TARGET_PATH}"
if command -v hf >/dev/null 2>&1; then
hf download "${MODEL_REPO}" --local-dir "${TARGET_PATH}" --max-workers 8
else
python3 - <<PY
from huggingface_hub import snapshot_download
snapshot_download(repo_id="${MODEL_REPO}", local_dir="${TARGET_PATH}", max_workers=8)
PY
fi
echo "Staged ${MODEL_REPO} under ${TARGET_PATH}"
echo "This is an acquisition/staging path only. The live L4 runtime remains qwen3.6:35b-a3b unless explicitly cut over."
echo "Use MODEL_REPO=txn545/Qwen3.5-122B-A10B-NVFP4 only on hardware validated for NVFP4."