Update app.py

app.py

@@ -3,8 +3,8 @@ from llama_cpp import Llama
 
 # Initialize the model
 llm = Llama.from_pretrained(
-    repo_id="simonper/Llama-3.2-1B-bnb-4bit_finetome-100k_gguf_3epochs_4bit",
-    filename="Llama-3.2-1B.Q4_K_M.gguf",
+    repo_id="simonper/fine-tuned-gguf-modal1",
+    filename="Llama-3.2-1B.Q8_0.gguf",
     n_ctx=2048,
     n_threads=2,
     verbose=False