Improve usability of --model-url & related flags (#6930)

* args: default --model to models/ + filename from --model-url or --hf-file (or else legacy models/7B/ggml-model-f16.gguf)

* args: main & server now call gpt_params_handle_model_default

* args: define DEFAULT_MODEL_PATH + update cli docs

* curl: check url of previous download (.json metadata w/ url, etag & lastModified)

* args: fix update to quantize-stats.cpp

* curl: support legacy .etag / .lastModified companion files

* curl: rm legacy .etag file support

* curl: reuse regex across headers callback calls

* curl: unique_ptr to manage lifecycle of curl & outfile

* curl: nit: no need for multiline regex flag

* curl: update failed test (model file collision) + gitignore *.gguf.json

1 files changed, 3 insertions, 1 deletions

diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index 2760aea8..01453af2 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -2353,7 +2353,7 @@ static void server_print_usage(const char * argv0, const gpt_params & params, co
         printf("                            disable KV offload\n");
     }
     printf("  -m FNAME, --model FNAME\n");
-    printf("                            model path (default: %s)\n", params.model.c_str());
+    printf("                            model path (default: models/$filename with filename from --hf-file or --model-url if set, otherwise %s)\n", DEFAULT_MODEL_PATH);
     printf("  -mu MODEL_URL, --model-url MODEL_URL\n");
     printf("                            model download url (default: unused)\n");
     printf("  -hfr REPO, --hf-repo REPO\n");
@@ -2835,6 +2835,8 @@ static void server_params_parse(int argc, char ** argv, server_params & sparams,
         }
     }
 
+    gpt_params_handle_model_default(params);
+
     if (!params.kv_overrides.empty()) {
         params.kv_overrides.emplace_back();
         params.kv_overrides.back().key[0] = 0;