Update app.py

app.py

@@ -10,7 +10,7 @@ def load_model():
     # Load the model from the Hugging Face Hub
     model = Llama.from_pretrained(
         repo_id="gallen881/Llama-3-8B-Physics_Master-GGUF",
-        filename="unsloth.F16.gguf"  # or unsloth.Q4_K_M.gguf for a smaller file
+        filename= "unsloth.Q4_K_M.gguf" # or unsloth.F16.gguf for a larger file
     )
     return model