Update app.py

app.py

@@ -32,10 +32,10 @@ import torch
 from huggingface_hub import hf_hub_download
 import os
 
-# Efficient GGUF model download and loading
+# Efficient GGUF model download and loading... i think....
 def download_and_load_model(
-    repo_id="HuggingFaceH4/zephyr-7b-beta", 
-    filename="zephyr-7b-beta.Q4_K_M.gguf"
+    repo_id="N-Bot-Int/OpenElla3-Llama3.2B-GGUF", 
+    filename="unsloth.Q4_K_M.gguf
 ):
     """
     Download GGUF model from HuggingFace if not exists