first commit

detect_tokenizer.py

@@ -0,0 +1,25 @@
+import os
+import json
+
+def detect(model_dir):
+    cfg_path = os.path.join(model_dir, "tokenizer_config.json")
+
+    if os.path.exists(cfg_path):
+        with open(cfg_path) as f:
+            cfg = json.load(f)
+        cls = cfg.get("tokenizer_class", "")
+    else:
+        cls = ""
+
+    files = os.listdir(model_dir)
+
+    if "tokenizer.json" in files:
+        return "fast", cls
+
+    if "tokenizer.model" in files:
+        return "sentencepiece", cls
+
+    if "vocab.json" in files and "merges.txt" in files:
+        return "bpe", cls
+
+    return "unknown", cls