update current model when we generate_stats()

llm_server/pages/about.py

@@ -0,0 +1 @@
+# TODO: add an about page

llm_server/pages/api.py

@@ -0,0 +1 @@
+# TODO: explain the API, how to use it, the endpoints

llm_server/routes/v1/generate_stats.py

@@ -13,11 +13,12 @@ from llm_server.routes.stats import SemaphoreCheckerThread, calculate_avg_gen_ti
 # TODO: have routes/__init__.py point to the latest API version generate_stats()
 
 def generate_stats():
-    model_list, error = get_running_model()  # will return False when the fetch fails
-    if isinstance(model_list, bool):
+    model_name, error = get_running_model()  # will return False when the fetch fails
+    if isinstance(model_name, bool):
         online = False
     else:
         online = True
+        opts.running_model = model_name
 
     # t = elapsed_times.copy()  # copy since we do multiple operations and don't want it to change
     # if len(t) == 0:
@@ -59,7 +60,7 @@ def generate_stats():
             'gatekeeper': 'none' if opts.auth_required is False else 'token',
             'context_size': opts.context_size,
             'queue_size': opts.concurrent_gens,
-            'model': model_list,
+            'model': model_name,
             'mode': opts.mode,
         },
         'keys': {