diff --git a/quantize.cpp b/quantize.cpp
index 14c7b277a4024a..10bed7db392dc8 100644
--- a/quantize.cpp
+++ b/quantize.cpp
@@ -122,8 +122,13 @@ bool llama_model_quantize(const std::string & fname_inp, const std::string & fna
             finp.read ((char *) word.data(), len);
             fout.write((char *) word.data(), len);
 
+            float score;
+            finp.read ((char *) &score, sizeof(score));
+            fout.write((char *) &score, sizeof(score));
+
             vocab.token_to_id[word] = i;
             vocab.id_to_token[i] = word;
+            vocab.score[i] = score;
         }
     }