NVIDIA Llama Nemotron Embed 1B v2

set -euo pipefail
# Forge API smoke test
# Forge selected target: route=/v1/embeddings model=nvidia-llama-nemotron-embed-1b-v2 version=v1 gpu=RTX6000 region=us-central1
FORGE_API_BASE=${FORGE_API_BASE:-'https://YOUR_FORGE_HOST'}
export MODEL_OR_FAMILY_SLUG=${MODEL_OR_FAMILY_SLUG:-'nvidia-llama-nemotron-embed-1b-v2'}
export FORGE_MODEL_VERSION=${FORGE_MODEL_VERSION:-'v1'}
export FORGE_GPU_TYPE=${FORGE_GPU_TYPE:-'RTX6000'}
export FORGE_REGION=${FORGE_REGION:-'us-central1'}
case "${FORGE_API_KEY:-}" in
  ""|replace-with-your-forge-api-key)
    echo 'Set FORGE_API_KEY to a real Forge API key before running this snippet; browser SSO sessions are not sent to copied curl or SDK clients.' >&2
    exit 1
    ;;
esac
forge_api_url() {
  endpoint="$1"
  base="${FORGE_API_BASE%/}"
  case "$base:$endpoint" in
    */v1:/v1|*/v1:/v1/*|*/v1:/v1\?*) printf '%s%s\n' "$base" "${endpoint#/v1}" ;;
    *) printf '%s%s\n' "$base" "$endpoint" ;;
  esac
}
python3 - <<'PY' |
import json
import os

payload = {
    "model": os.environ["MODEL_OR_FAMILY_SLUG"],
    "input": "Forge API smoke test",
}
model_version = os.environ.get("FORGE_MODEL_VERSION")
if model_version:
    payload["model_version"] = model_version
gpu_type = os.environ.get("FORGE_GPU_TYPE", "RTX6000")
if gpu_type:
    payload["gpu_type"] = gpu_type
region = os.environ.get("FORGE_REGION", "us-central1")
if region:
    payload["region"] = region
print(json.dumps(payload))
PY
curl -sS --fail-with-body "$(forge_api_url '/v1/embeddings')" \
  --max-time "${FORGE_REQUEST_TIMEOUT_SECONDS:-600}" \
  -X POST \
  -H "Authorization: Bearer ${FORGE_API_KEY}" \
  -H "Content-Type: application/json" \
  -d @- | \
python3 -c 'import json, sys

data = json.load(sys.stdin)
embedding = ((data.get("data") or [{}])[0].get("embedding"))
if isinstance(embedding, list):
    print(json.dumps(embedding[:8]))
else:
    print(json.dumps(data, indent=2))'