scripts/push_to_hub.py

#!/usr/bin/env python3
"""
Push zindango-slm to Hugging Face Hub.
Usage:
  python scripts/push_to_hub.py [--model-dir PATH] [--repo-id USERNAME/zindango-slm]
Requires: huggingface-cli login (or HF_TOKEN env)
"""

import argparse
from pathlib import Path

from huggingface_hub import HfApi, create_repo, upload_folder


def main():
    parser = argparse.ArgumentParser(description="Push zindango-slm to Hugging Face Hub")
    parser.add_argument(
        "--model-dir",
        type=str,
        default="outputs/zindango-slm-20260215_124754",
        help="Local model directory to upload",
    )
    parser.add_argument(
        "--repo-id",
        type=str,
        default=None,
        help="Hub repo ID (username/zindango-slm). Default: infer from login",
    )
    parser.add_argument(
        "--private",
        action="store_true",
        help="Create private repository",
    )
    parser.add_argument(
        "--skip-create",
        action="store_true",
        help="Skip create_repo (use if repo already exists or create manually at https://huggingface.co/new)",
    )
    args = parser.parse_args()

    model_dir = Path(args.model_dir)
    if not model_dir.exists():
        raise SystemExit(f"Model directory not found: {model_dir}")

    api = HfApi()
    try:
        user = api.whoami()
        username = user["name"]
    except Exception as e:
        raise SystemExit(
            f"Not logged in to Hugging Face. Run: huggingface-cli login\nError: {e}"
        )

    repo_id = args.repo_id or f"{username}/zindango-slm"
    print(f"Uploading to https://huggingface.co/{repo_id}")

    # Create repo if needed (skip if --skip-create or 403)
    if not args.skip_create:
        try:
            create_repo(repo_id, repo_type="model", private=args.private, exist_ok=True)
        except Exception as e:
            err = str(e).lower()
            if "403" in err or "forbidden" in err or "rights" in err:
                print("Note: Could not create repo (check token write access).")
                print("Create it manually at: https://huggingface.co/new")
                print("Then run with: --skip-create")
                raise
            if "already exists" not in err and "409" not in err:
                raise

    # Exclude checkpoint subdir and training artifacts
    ignore_patterns = ["checkpoint-*", "training_args.bin", "*.pt", ".git*"]

    upload_folder(
        folder_path=str(model_dir),
        repo_id=repo_id,
        repo_type="model",
        ignore_patterns=ignore_patterns,
        commit_message="Upload zindango-slm: SFT for Zindango (English-only)",
    )
    print(f"Done. Model: https://huggingface.co/{repo_id}")


if __name__ == "__main__":
    main()