5dfc4a9fad
Rebuild the repo so its spine is a real, reproducible demonstration of
licensing an actual model capability, not payload-agnostic crypto on
stand-in blobs. The clean-room Ed25519 + AES-256-GCM primitives stay as
the fast mechanism layer; the real thing is now the headline.
New demo/ walkthrough (steps 1-7), each a standalone script printing
machine-checked evidence:
1 download Qwen2.5-0.5B-Instruct from Hugging Face (gitignored cache)
2 base scores 0.000 on an invented tool-call protocol (capability C)
3 train a PEFT LoRA on C, base frozen (SHA-256 byte-identical proof)
4 base + LoRA scores 0.925 on a held-out set with unseen arguments
5 seal the adapter as an AES-256-GCM unit under an Ed25519 leaf cert
6 valid licence decrypts-at-load and runs C at 0.925
7 access-gate then crypto-erase: original and exfiltrated copy both
permanently undecryptable, base alone back to 0.000
Reference run on an RTX 4090 captured the observed numbers now in the
README. keystore.py gains export_state/load_state so the authority (and
crypto-erasure) persists across the separate demo commands. A single
run_demo.sh drives steps 1-7; run_all.sh + pytest remain the fast
crypto-only mechanism tests.
Ships code only: base weights, HF cache, trained adapter, wrapping keys
and every sealed unit are gitignored and never committed. README rewritten
to lead with the demo and the observed numbers, with honest bounds
(in-memory adapter during a live licence needs a hardware enclave) and a
capability-tree scale-up as future work.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
57 lines
2 KiB
Python
57 lines
2 KiB
Python
#!/usr/bin/env python3
|
|
"""Step 1: download the base model from Hugging Face into a gitignored cache.
|
|
|
|
Prints the exact model id, where the weights landed locally, the on-disk size,
|
|
and the parameter count. Nothing here is committed: the cache directory is
|
|
gitignored, and the reviewer pulls the weights themselves by running this step.
|
|
"""
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
|
|
|
|
from demo.common import BASE_MODEL_ID, HF_CACHE, HF_LINK
|
|
|
|
|
|
def _dir_size_bytes(path: Path) -> int:
|
|
return sum(p.stat().st_size for p in path.rglob("*") if p.is_file())
|
|
|
|
|
|
def main() -> int:
|
|
print("=== Step 1: download base model ===\n")
|
|
print(f" model id: {BASE_MODEL_ID}")
|
|
print(f" hugging face: {HF_LINK}")
|
|
print(f" cache dir: {HF_CACHE} (gitignored)\n")
|
|
|
|
from huggingface_hub import snapshot_download
|
|
from transformers import AutoConfig
|
|
|
|
local_path = snapshot_download(repo_id=BASE_MODEL_ID)
|
|
config = AutoConfig.from_pretrained(BASE_MODEL_ID)
|
|
|
|
n_params = None
|
|
# Derive parameter count cheaply from config where possible, else load.
|
|
try:
|
|
from transformers import AutoModelForCausalLM
|
|
|
|
model = AutoModelForCausalLM.from_pretrained(BASE_MODEL_ID)
|
|
n_params = sum(p.numel() for p in model.parameters())
|
|
del model
|
|
except Exception as exc: # pragma: no cover - informational only
|
|
print(f" (parameter count skipped: {exc})")
|
|
|
|
size_gib = _dir_size_bytes(Path(local_path)) / 2**30
|
|
print(f" downloaded to: {local_path}")
|
|
print(f" on-disk size: {size_gib:.2f} GiB")
|
|
if n_params is not None:
|
|
print(f" parameters: {n_params:,} ({n_params / 1e6:.0f}M)")
|
|
print(f" architecture: {config.architectures}")
|
|
print(f" hidden_size={config.hidden_size}, layers={config.num_hidden_layers}")
|
|
|
|
print("\nRESULT: PASS - base model present locally and ready to run.")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|