| import hashlib |
| import json |
| import random |
| import sys |
| from pathlib import Path |
|
|
| ROOT = Path(__file__).resolve().parents[1] |
|
|
| def dump(path, value): |
| path = Path(path) |
| path.parent.mkdir(parents=True, exist_ok=True) |
| path.write_text(json.dumps(value, ensure_ascii=False, indent=2), encoding="utf-8") |
|
|
| def load(path): |
| return json.loads(Path(path).read_text(encoding="utf-8")) |
|
|
| def jsonl(path, rows): |
| path = Path(path) |
| path.parent.mkdir(parents=True, exist_ok=True) |
| with path.open("w", encoding="utf-8") as f: |
| for row in rows: |
| f.write(json.dumps(row, ensure_ascii=False) + "\n") |
|
|
| def seed_all(seed=42): |
| import numpy as np |
| import torch |
| random.seed(seed) |
| np.random.seed(seed) |
| torch.manual_seed(seed) |
| torch.cuda.manual_seed_all(seed) |
| torch.backends.cudnn.deterministic = True |
| torch.backends.cudnn.benchmark = False |
| torch.set_num_threads(6) |
|
|
| def environment(): |
| import importlib.metadata as m |
| import torch |
| packages = {} |
| for name in ["torch", "transformers", "tokenizers", "numpy", "pandas", "scikit-learn", "gradio", "easyjailbreak"]: |
| try: |
| packages[name] = m.version(name) |
| except m.PackageNotFoundError: |
| packages[name] = None |
| return dict(python=sys.version, executable=sys.executable, packages=packages, |
| cuda=torch.version.cuda, gpu=torch.cuda.get_device_name(0) if torch.cuda.is_available() else None) |
|
|
| def sha256(path): |
| h = hashlib.sha256() |
| with Path(path).open("rb") as f: |
| for b in iter(lambda: f.read(2**20), b""): |
| h.update(b) |
| return h.hexdigest() |
|
|
