cache-hf-model.yml

# Copyright (c) 2025, NVIDIA CORPORATION.  All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
name: "Cache HuggingFace Model"

on:
  workflow_dispatch:
    inputs:
      hf-model-id:
        type: string
        description: HuggingFace repo ID of the model to cache
        required: true

jobs:
  download:
    name: Download Model
    runs-on: self-hosted-nemo
    environment: nemo-ci
    env:
      HF_HUB_OFFLINE: 0
      HF_HOME: /mnt/datadrive/TestData/HF_HOME
    steps:
      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: "3.12"

      - name: Install dependencies
        run: |
          pip install torch transformers "huggingface_hub[cli]"

      - name: Log in to HuggingFace
        env:
          HF_ACCESS_TOKEN: ${{ secrets.HF_ACCESS_TOKEN }}
        run: |
            hf auth login --token ${HF_ACCESS_TOKEN}

      - name: Download model
        env:
          MODEL_ID: ${{ github.event.inputs.hf-model-id }}
        shell: python
        run: |
          import os
          from transformers import AutoModel
          _ = AutoModel.from_pretrained(os.getenv("MODEL_ID"))