#!/usr/bin/env python3 # 检测 tokenizer 是否需要修复 import json import os MODEL_DIR = os.environ.get("MODEL_DIR", "/model") cfg_path = os.path.join(MODEL_DIR, "tokenizer_config.json") if not os.path.exists(cfg_path): print("no tokenizer_config.json") raise SystemExit(0) with open(cfg_path, "r", encoding="utf-8") as f: cfg = json.load(f) if cfg.get("tokenizer_class") in {"TokenizersBackend", "TiktokenTokenizer"}: print("need_fix") elif isinstance(cfg.get("extra_special_tokens"), list): print("need_fix") else: print("ok")