try

2025-07-04 15:50:43 +04:00 · 2025-07-04 15:50:43 +04:00 · 1fd0574adc
parent a6d0067dd7
commit 1fd0574adc
1 changed files with 4 additions and 1 deletions
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@ -607,7 +607,10 @@ class TextModel(ModelBase):

        from transformers import AutoTokenizer
        tokenizer = AutoTokenizer.from_pretrained(self.dir_model)
-        vocab_size = self.hparams.get("vocab_size", len(tokenizer.vocab))
+        vocab_size = max(
+            self.hparams.get("vocab_size", len(tokenizer.vocab)),
+            len(tokenizer.vocab)
+        )
        assert max(tokenizer.vocab.values()) < vocab_size

        tokpre = self.get_vocab_base_pre(tokenizer)