convert : fix encoding of WPM vocab for BERT models (#18500)

* convert: avoid token collision when stripping ## prefix

* convert: use token types for BERT special tokens check

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

convert_hf_to_gguf.py

@@ -5287,13 +5287,14 @@ class BertModel(TextModel):
         self.gguf_writer.add_token_type_count(self.hparams.get("type_vocab_size", 1))
 
         # convert to phantom space vocab
-        def phantom(tok):
-            if tok.startswith("[") and tok.endswith("]"):
+        def phantom(tok, toktype):
+            if toktype == gguf.TokenType.CONTROL:
                 return tok
             if tok.startswith("##"):
                 return tok[2:]
             return "\u2581" + tok
-        tokens = list(map(phantom, tokens))
+        assert len(tokens) == len(toktypes)
+        tokens = list(map(phantom, tokens, toktypes))
 
         # add vocab to gguf
         self.gguf_writer.add_tokenizer_model("bert")