diff --git a/tests/test-tokenizer-0.cpp b/tests/test-tokenizer-0.cpp
index 0c2d7781b..1f04b6f34 100644
--- a/tests/test-tokenizer-0.cpp
+++ b/tests/test-tokenizer-0.cpp
@@ -195,7 +195,7 @@ int main(int argc, char **argv) {
     const bool add_special = false;
 
     for (const auto & test_kv : k_tests) {
-        const std::vector<llama_token> res = llama_tokenize(ctx, test_kv.first, add_special);
+        const std::vector<llama_token> res = llama_tokenize(ctx, test_kv.first, add_special, true);
 
         printf("\n");
         printf("src: '%s'\n", test_kv.first.c_str());
@@ -253,7 +253,7 @@ int main(int argc, char **argv) {
         {
             const auto t_start = ggml_time_us();
 
-            res = llama_tokenize(ctx, text, add_special);
+            res = llama_tokenize(ctx, text, add_special, true);
 
             const auto t_end = ggml_time_us();
 
diff --git a/tests/test-tokenizer-1-spm.cpp b/tests/test-tokenizer-1-spm.cpp
index 8c7093489..e82da302c 100644
--- a/tests/test-tokenizer-1-spm.cpp
+++ b/tests/test-tokenizer-1-spm.cpp
@@ -62,8 +62,8 @@ int main(int argc, char ** argv) {
     const int n_vocab = llama_n_vocab(model);
 
     for (int i = 0; i < n_vocab; ++i) {
-        std::string str = llama_detokenize(ctx, std::vector<int>(1, i));
-        std::vector<llama_token> tokens = llama_tokenize(ctx, str, false);
+        std::string str = llama_detokenize(ctx, std::vector<int>(1, i), true);
+        std::vector<llama_token> tokens = llama_tokenize(ctx, str, false, true);
         std::string check = llama_detokenize(ctx, tokens);
         if (check != str) {
             fprintf(stderr, "%s : error: token %d detokenizes to '%s'(%zu) but tokenization of this detokenizes to '%s'(%zu)\n",
@@ -86,7 +86,7 @@ int main(int argc, char ** argv) {
                     }
 
                     std::string str = unicode_cpt_to_utf8(cp);
-                    std::vector<llama_token> tokens = llama_tokenize(ctx, str, false);
+                    std::vector<llama_token> tokens = llama_tokenize(ctx, str, false, true);
                     std::string check = llama_detokenize(ctx, tokens);
                     if (cp != 9601 && str != check) {
                         fprintf(stderr, "error: codepoint %x detokenizes to '%s'(%zu) instead of '%s'(%zu)\n",