diff --git a/llama.cpp b/llama.cpp
index ae6d81b88..578ee9bf4 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -8542,10 +8542,10 @@ struct llama_model_params llama_model_default_params() {
         /*.tensor_split                =*/ nullptr,
         /*.progress_callback           =*/ nullptr,
         /*.progress_callback_user_data =*/ nullptr,
+        /*.kv_overrides                =*/ nullptr,
         /*.vocab_only                  =*/ false,
         /*.use_mmap                    =*/ true,
         /*.use_mlock                   =*/ false,
-        /*.kv_overrides                =*/ nullptr,
     };
 
 #ifdef GGML_USE_METAL
diff --git a/llama.h b/llama.h
index cc3fb53ba..8175c8139 100644
--- a/llama.h
+++ b/llama.h
@@ -181,14 +181,17 @@ extern "C" {
 
         // called with a progress value between 0 and 1, pass NULL to disable
         llama_progress_callback progress_callback;
+
         // context pointer passed to the progress callback
         void * progress_callback_user_data;
 
+        // override key-value pairs of the model meta data
+        const struct llama_model_kv_override * kv_overrides;
+
         // Keep the booleans together to avoid misalignment during copy-by-value.
         bool vocab_only; // only load the vocabulary, no weights
         bool use_mmap;   // use mmap if possible
         bool use_mlock;  // force system to keep model in RAM
-        const struct llama_model_kv_override * kv_overrides;
     };
 
     struct llama_context_params {