Enable fi-daily-research-brief, prove fi_brief_status idempotence with the 2026-07-28 brief, approve R/S catalog entries, collect and verify embeds plus Qwen3-8B and R1-Distill-14B on VAULT, and document residuals (HF-gated Llama, deferred S giants, railiance ConfigMap apply).
153 lines
4 KiB
Python
Executable file
153 lines
4 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
"""Collect one HF model into the VAULT reserve tree (weights-first).
|
|
|
|
Usage:
|
|
/tmp/fi-hf/bin/python scripts/collect_model.py \\
|
|
--repo-id Qwen/Qwen3-8B --local-name Qwen__Qwen3-8B --revision main
|
|
|
|
Layout:
|
|
{base}/models/{local_name}/{revision}/ # HF files (no full onnx dump)
|
|
{base}/staging/... # incomplete
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import hashlib
|
|
import json
|
|
import os
|
|
import shutil
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
# Prefer sequential downloads on WSL+drvfs (xet parallel can OOM)
|
|
os.environ.setdefault("HF_HUB_DISABLE_XET", "1")
|
|
|
|
from huggingface_hub import snapshot_download # noqa: E402
|
|
|
|
DEFAULT_ALLOW = (
|
|
"*.safetensors",
|
|
"*.bin",
|
|
"*.json",
|
|
"*.txt",
|
|
"*.model",
|
|
"*.tiktoken",
|
|
"tokenizer*",
|
|
"vocab*",
|
|
"merges.txt",
|
|
"special_tokens_map.json",
|
|
"generation_config.json",
|
|
"configuration*.py",
|
|
"modeling*.py",
|
|
"README.md",
|
|
"LICENSE*",
|
|
"*.md",
|
|
# sentence-transformers / embed extras
|
|
"1_Pooling/*",
|
|
"modules.json",
|
|
"sentence_*",
|
|
"config_sentence_transformers.json",
|
|
)
|
|
|
|
IGNORE = (
|
|
"onnx/*",
|
|
"openvino/*",
|
|
"flax_model*",
|
|
"tf_model*",
|
|
"rust_model*",
|
|
"*.ot",
|
|
"*.h5",
|
|
"imgs/*",
|
|
".gitattributes",
|
|
)
|
|
|
|
|
|
def sha256_file(path: Path, chunk: int = 8 * 1024 * 1024) -> str:
|
|
h = hashlib.sha256()
|
|
with path.open("rb") as f:
|
|
while True:
|
|
b = f.read(chunk)
|
|
if not b:
|
|
break
|
|
h.update(b)
|
|
return h.hexdigest()
|
|
|
|
|
|
def main() -> int:
|
|
ap = argparse.ArgumentParser()
|
|
ap.add_argument("--repo-id", required=True)
|
|
ap.add_argument("--local-name", required=True)
|
|
ap.add_argument("--revision", default="main")
|
|
ap.add_argument(
|
|
"--base",
|
|
default="/mnt/d/vault/coulomb/freedom-intelligence",
|
|
)
|
|
ap.add_argument("--token", default=os.environ.get("HF_TOKEN") or None)
|
|
args = ap.parse_args()
|
|
|
|
base = Path(args.base)
|
|
stage = base / "staging" / args.local_name / args.revision
|
|
final = base / "models" / args.local_name / args.revision
|
|
|
|
if final.exists() and any(final.rglob("*.safetensors")) or (
|
|
final.exists() and any(final.rglob("pytorch_model*.bin"))
|
|
):
|
|
print(f"already present with weights: {final}")
|
|
return 0
|
|
|
|
if stage.exists():
|
|
shutil.rmtree(stage, ignore_errors=True)
|
|
stage.mkdir(parents=True, exist_ok=True)
|
|
|
|
print(f"downloading {args.repo_id}@{args.revision} -> {stage}")
|
|
snapshot_download(
|
|
repo_id=args.repo_id,
|
|
revision=args.revision,
|
|
local_dir=str(stage),
|
|
allow_patterns=list(DEFAULT_ALLOW),
|
|
ignore_patterns=list(IGNORE),
|
|
token=args.token,
|
|
max_workers=1,
|
|
)
|
|
|
|
# strip hub cache dir if present
|
|
cache = stage / ".cache"
|
|
if cache.exists():
|
|
shutil.rmtree(cache, ignore_errors=True)
|
|
|
|
final.parent.mkdir(parents=True, exist_ok=True)
|
|
if final.exists():
|
|
shutil.rmtree(final)
|
|
shutil.move(str(stage), str(final))
|
|
|
|
artifacts = []
|
|
total = 0
|
|
for p in sorted(final.rglob("*")):
|
|
if not p.is_file():
|
|
continue
|
|
if p.name.startswith("."):
|
|
continue
|
|
rel = str(p.relative_to(final))
|
|
# hash only weight-like files (cheap for small; large still OK sequential)
|
|
if p.suffix in {".safetensors", ".bin", ".gguf", ".pt"} or p.stat().st_size > 1_000_000:
|
|
digest = sha256_file(p)
|
|
else:
|
|
digest = ""
|
|
size = p.stat().st_size
|
|
total += size
|
|
artifacts.append({"path": rel, "sha256": digest, "bytes": size})
|
|
|
|
manifest = {
|
|
"repo_id": args.repo_id,
|
|
"revision": args.revision,
|
|
"local_name": args.local_name,
|
|
"storage_path": str(final),
|
|
"total_bytes": total,
|
|
"artifacts": artifacts,
|
|
}
|
|
(final / "MANIFEST.json").write_text(json.dumps(manifest, indent=2) + "\n")
|
|
print(json.dumps({"ok": True, "total_bytes": total, "path": str(final)}, indent=2))
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|