Update app.py

app.py

@@ -8,8 +8,8 @@ import numpy as np
 
 model = Llama(
     model_path=hf_hub_download(
-        repo_id=os.environ.get("REPO_ID", "Lyte/QuadConnect2.5-0.5B-v0.0.2b"),
-        filename=os.environ.get("MODEL_FILE", "unsloth.Q8_0.gguf"),
+        repo_id=os.environ.get("REPO_ID", "Lyte/QuadConnect2.5-0.5B-v0.0.3b"),
+        filename=os.environ.get("MODEL_FILE", "quadconnect_q8_0.gguf"),
     )
 )