Update app.py

app.py

@@ -1,6 +1,7 @@
 print("START: BEFORE IMPORTS")
 
 import os
+impo
 import gradio as gr
 import copy
 from llama_cpp import Llama
@@ -10,19 +11,20 @@ print("START: AFTER IMPORTS")
 
 try:
     print("START: BEFORE MODEL DOWNLOAD")
+    start_load_time = time.time()
     model_path = hf_hub_download(
-        repo_id="NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF",
-        filename="Nous-Hermes-2-Mixtral-8x7B-DPO.Q4_K_M.gguf",
+        repo_id="NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF",
+        filename="Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf",
         
     )
-    print("START: AFTER MODEL DOWNLOAD")
+    print("START: AFTER MODEL DOWNLOAD -- " + time.time() - start_load_time + "s")
     llm = Llama(
         model_path=model_path,
         n_ctx=2048,
         n_gpu_layers=-1,  # change n_gpu_layers if you have more or less VRAM
         verbose=True
     )
-    print("START: AFTER LLAMA-CPP SETUP")
+    print("START: AFTER LLAMA-CPP SETUP -- " + time.time() - start_load_time + "s")
 
 except Exception as e:
     print(e)