examples: cache hf model when --model not provided

common/common.cpp

@@ -1354,8 +1354,7 @@ void gpt_params_handle_model_default(gpt_params & params) {
             }
             params.hf_file = params.model;
         } else if (params.model.empty()) {
-            const char* cache_dir = getenv("LLAMA_CACHE") ? getenv("LLAMA_CACHE") : DEFAULT_LLAMA_CACHE;
+            params.model = get_cache_directory() + string_split(params.hf_file, '/').back();
-            params.model = cache_dir + string_split(params.hf_file, '/').back();
         }
     } else if (!params.model_url.empty()) {
         if (params.model.empty()) {
@@ -2528,6 +2527,37 @@ bool create_directory_with_parents(const std::string & path) {
 #endif // _WIN32
 }
 
+std::string get_cache_directory() {
+    std::string cache_directory = "";
+    if (getenv("LLAMA_CACHE")) {
+        cache_directory = std::getenv("LLAMA_CACHE");
+        if (cache_directory.back() != DIRECTORY_SEPARATOR) {
+            cache_directory += DIRECTORY_SEPARATOR;
+        }
+    } else {
+#ifdef __linux__
+        if (std::getenv("XDG_CACHE_HOME")) {
+            cache_directory = std::getenv("XDG_CACHE_HOME");
+        } else {
+            cache_directory = std::getenv("HOME") + std::string("/.cache/");
+        }
+#elif defined(__APPLE__)
+        cache_directory = std::getenv("HOME") + std::string("/Library/Caches/");
+#elif defined(_WIN32)
+        cache_directory = std::getenv("APPDATA");
+#endif // __linux__
+        cache_directory += "llama.cpp";
+        cache_directory += DIRECTORY_SEPARATOR;
+    }
+
+    const bool success = create_directory_with_parents(cache_directory);
+    if (!success) {
+        throw std::runtime_error("failed to create cache directory: " + cache_directory);
+    }
+
+    return cache_directory;
+}
+
 void dump_vector_float_yaml(FILE * stream, const char * prop_name, const std::vector<float> & data) {
     if (data.empty()) {
         fprintf(stream, "%s:\n", prop_name);

common/common.h

@@ -287,6 +287,7 @@ bool llama_should_add_bos_token(const llama_model * model);
 //
 
 bool create_directory_with_parents(const std::string & path);
+std::string get_cache_directory();
 void dump_vector_float_yaml(FILE * stream, const char * prop_name, const std::vector<float> & data);
 void dump_vector_int_yaml(FILE * stream, const char * prop_name, const std::vector<int> & data);
 void dump_string_yaml_multiline(FILE * stream, const char * prop_name, const char * data);