Update app.py

app.py

@@ -4,8 +4,7 @@ from typing import List, Tuple, Iterator
 from huggingface_hub.utils import HfHubHTTPError
 
 # Custom HuggingFace Inference endpoint
-ENDPOINT = "https://njy777sn6evjwzkp.us-east4.gcp.endpoints.huggingface.cloud"
-
+MODEL_ID = Dushyant4342/ft-llama3-8b-credit-analyst
 # Context window constraints (Llama‑3‑8B supports ~4096 tokens)
 CONTEXT_WINDOW = 4096
 RESERVED_TOKENS = 512  # reserve space for response