| """Export local HF Falcon-H1 safetensors into exact-name f32 FH1W tensor pack. |
| |
| Dependencies: pip install safetensors torch huggingface_hub |
| Example: |
| python tools/export.py --repo tiiuae/Falcon-H1-0.5B-Instruct --output falcon-h1.f32pack |
| |
| The 0.5B model is ~2 GB in float32; this is CPU reference, not a GPU converter. |
| """ |
| import argparse |
| import struct |
| from pathlib import Path |
| from huggingface_hub import snapshot_download |
| from safetensors import safe_open |
|
|
|
|
| def convert(model_dir: Path, output: Path): |
| paths = sorted(model_dir.glob("*.safetensors")) |
| if not paths: |
| raise ValueError("No safetensors files in selected model directory") |
| |
| entries = [] |
| for path in paths: |
| with safe_open(str(path), framework="pt", device="cpu") as sf: |
| for name in sf.keys(): |
| if name.startswith(("model.", "lm_head.")): |
| entries.append((path, name)) |
| if len(entries) > 50000: |
| raise ValueError("Too many checkpoint tensors") |
| output.parent.mkdir(parents=True, exist_ok=True) |
| with output.open("wb") as f: |
| f.write(b"FH1W") |
| f.write(struct.pack("<I", len(entries))) |
| for path, name in entries: |
| with safe_open(str(path), framework="pt", device="cpu") as sf: |
| tensor = sf.get_tensor(name).float().contiguous() |
| name_b = name.encode("utf-8") |
| shape = tuple(tensor.shape) |
| if not (1 <= len(shape) <= 4): |
| raise ValueError((name, shape)) |
| f.write(struct.pack("<H", len(name_b))) |
| f.write(name_b) |
| f.write(struct.pack("<B", len(shape))) |
| for dim in shape: |
| f.write(struct.pack("<I", dim)) |
| f.write(tensor.numpy().astype("<f4", copy=False).tobytes()) |
| print(f"Wrote {len(entries)} named float32 tensors: {output}") |
|
|
|
|
| if __name__ == "__main__": |
| p = argparse.ArgumentParser() |
| p.add_argument("--repo", default="tiiuae/Falcon-H1-0.5B-Instruct") |
| p.add_argument("--local", help="Use an already downloaded model directory") |
| p.add_argument("--output", default="falcon-h1.f32pack") |
| a = p.parse_args() |
| root = Path(a.local) if a.local else Path(snapshot_download(repo_id=a.repo, allow_patterns=["*.safetensors", "*.json"])) |
| convert(root, Path(a.output)) |
|
|
