diff --git a/src/llama-vocab.cpp b/src/llama-vocab.cpp
index 4d054db..00c7c68 100644
--- a/src/llama-vocab.cpp
+++ b/src/llama-vocab.cpp
@@ -537,7 +537,7 @@ struct llm_tokenizer_bpe : llm_tokenizer {
                 break;
             case LLAMA_VOCAB_PRE_TYPE_K2_HORIZON:
                 regex_exprs = {
-                    "(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\r\\n\\p{L}\\p{N}]?(?:\\p{L}|\\p{M}|\\u200C|\\u200D)+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+                    "(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\r\\n\\p{L}\\p{N}]?(?:\\p{L}|\\p{M})+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
                 };
                 break;
             case LLAMA_VOCAB_PRE_TYPE_WHITESPACE: