fix regression

Author: ngxson

convert_hf_to_gguf.py

@@ -607,6 +607,7 @@ def get_vocab_base(self) -> tuple[list[str], list[int], str]:
 
         from transformers import AutoTokenizer
         tokenizer = AutoTokenizer.from_pretrained(self.dir_model)
+        vocab_size = self.hparams.get("vocab_size", len(tokenizer.vocab))
         assert max(tokenizer.vocab.values()) < vocab_size
 
         tokpre = self.get_vocab_base_pre(tokenizer)