refactor model endpoint

Author: tastelikefeet

common/arg.cpp

@@ -228,6 +228,7 @@ static bool common_download_file_single(const std::string & url, const std::stri
     curl_easy_setopt(curl.get(), CURLOPT_URL, url.c_str());
     curl_easy_setopt(curl.get(), CURLOPT_FOLLOWLOCATION, 1L);
 
+    http_headers.ptr = curl_slist_append(http_headers.ptr, "User-Agent: llama-cpp");
     // Check if hf-token or bearer-token was specified
     if (!bearer_token.empty()) {
         std::string auth_header = "Authorization: Bearer " + bearer_token;
@@ -374,7 +375,6 @@ static bool common_download_file_single(const std::string & url, const std::stri
 
         //  display download progress
         curl_easy_setopt(curl.get(), CURLOPT_NOPROGRESS, 0L);
-        curl_easy_setopt(curl.get(), CURLOPT_USERAGENT, "llama.cpp/1.0");
 
 
         // helper function to hide password in URL
@@ -547,12 +547,7 @@ static struct common_hf_file_res common_get_hf_file(const std::string & hf_repo_
     curl_slist_ptr http_headers;
     std::string res_str;
 
-    std::string model_endpoint = "https://huggingface.co/";
-    const char * model_endpoint_env = getenv("MODEL_ENDPOINT");
-    if (model_endpoint_env) {
-        model_endpoint = model_endpoint_env;
-        if (model_endpoint.back() != '/') model_endpoint += '/';
-    }
+    std::string model_endpoint = get_model_endpoint();
 
     std::string url = model_endpoint + "v2/" + hf_repo + "/manifests/" + tag;
     curl_easy_setopt(curl.get(), CURLOPT_URL, url.c_str());
@@ -669,12 +664,7 @@ static void common_params_handle_model(
                 }
             }
 
-            std::string model_endpoint = "https://huggingface.co/";
-            const char * model_endpoint_env = getenv("MODEL_ENDPOINT");
-            if (model_endpoint_env) {
-                model_endpoint = model_endpoint_env;
-                if (model_endpoint.back() != '/') model_endpoint += '/';
-            }
+            std::string model_endpoint = get_model_endpoint();
             model.url = model_endpoint + model.hf_repo + "/resolve/main/" + model.hf_file;
             // make sure model path is present (for caching purposes)
             if (model.path.empty()) {

common/common.cpp

@@ -1027,6 +1027,16 @@ struct common_init_result common_init_from_params(common_params & params) {
     return iparams;
 }
 
+std::string get_model_endpoint() {
+    std::string model_endpoint = "https://huggingface.co/";
+    const char * model_endpoint_env = getenv("MODEL_ENDPOINT");
+    if (model_endpoint_env) {
+        model_endpoint = model_endpoint_env;
+        if (model_endpoint.back() != '/') model_endpoint += '/';
+    }
+    return model_endpoint;
+}
+
 void common_set_adapter_lora(struct llama_context * ctx, std::vector<common_adapter_lora_info> & lora) {
     llama_clear_adapter_lora(ctx);
     for (auto & la : lora) {

common/common.h

@@ -543,6 +543,8 @@ struct ggml_threadpool_params ggml_threadpool_params_from_cpu_params(const cpu_p
 // clear LoRA adapters from context, then apply new list of adapters
 void common_set_adapter_lora(struct llama_context * ctx, std::vector<common_adapter_lora_info> & lora);
 
+std::string                   get_model_endpoint();
+
 //
 // Batch utils
 //

examples/run/run.cpp

@@ -697,12 +697,7 @@ class LlamaData {
         std::vector<std::string> headers = { "User-Agent: llama-cpp", "Accept: application/json" };
         std::string              url;
 
-        std::string model_endpoint = "https://huggingface.co/";
-        const char * model_endpoint_env = getenv("MODEL_ENDPOINT");
-        if (model_endpoint_env) {
-            model_endpoint = model_endpoint_env;
-            if (model_endpoint.back() != '/') model_endpoint += '/';
-        }
+        std::string model_endpoint = get_model_endpoint();
 
         if (pos == std::string::npos) {
             auto [model_name, manifest_url] = extract_model_and_tag(model, model_endpoint + "v2/");