Update app.py

app.py

@@ -1,19 +1,23 @@
+print("START: BEFORE IMPORTS")
+
 import os
 import gradio as gr
 import copy
 from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
 
+print("START: AFTER IMPORTS")
 
 try:
     llm = Llama(
         model_path=hf_hub_download(
-            repo_id=os.environ.get("REPO_ID", "microsoft/Phi-3-mini-4k-instruct-gguf"),
-            filename=os.environ.get("MODEL_FILE", "Phi-3-mini-4k-instruct-q4.gguf"),
+            repo_id="microsoft/Phi-3-mini-4k-instruct-gguf",
+            filename="*q4.gguf",
         ),
         n_ctx=2048,
         n_gpu_layers=-1,  # change n_gpu_layers if you have more or less VRAM
     )
+    print("START: AFTER LLAMA-CPP SETUP")
 
 except Exception as e:
     print(e)