cont : fix mmap flag print (#11699)

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index e30db66e94643a309b9c66fef9ef4c7a5d8130ff..0f4b62c434d4b3a8758a40f5df17c82ba9ee9c2d 100644 (file)
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -1275,7 +1275,7 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
 
     const bool use_mmap_buffer = true;
 
-    LLAMA_LOG_INFO("%s: loading model tensors, this can take a while... (mmap = %s)\n", __func__, use_mmap_buffer ? "true" : "false");
+    LLAMA_LOG_INFO("%s: loading model tensors, this can take a while... (mmap = %s)\n", __func__, ml.use_mmap ? "true" : "false");
 
     // build a list of buffer types for the CPU and GPU devices
     pimpl->cpu_buft_list = make_cpu_buft_list(devices);

diff --git a/src/llama.cpp b/src/llama.cpp
index 3b6a21d81f186c91c67723571d00366ff9121db9..607f27861596931ea50ecde86251f83040a539d2 100644 (file)
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -9430,7 +9430,6 @@ static struct llama_model * llama_model_load_from_file_impl(
         struct llama_model_params params) {
     ggml_time_init();
 
-
     unsigned cur_percentage = 0;
     if (params.progress_callback == NULL) {
         params.progress_callback_user_data = &cur_percentage;