diff --git a/convert-hf-to-gguf.py b/convert-hf-to-gguf.py
index 716809597..6a2ce187c 100755
--- a/convert-hf-to-gguf.py
+++ b/convert-hf-to-gguf.py
@@ -1065,6 +1065,7 @@ class LlamaModel(Model):
     def set_gguf_parameters(self):
         super().set_gguf_parameters()
         hparams = self.hparams
+        self.gguf_writer.add_vocab_size(hparams["vocab_size"])
         self.gguf_writer.add_rope_dimension_count(hparams["hidden_size"] // hparams["num_attention_heads"])
 
     # Same as super class, but permuting q_proj, k_proj