Update app.py

app.py

@@ -13,8 +13,8 @@ load_dotenv()
 
 # Configure the Llama index settings
 Settings.llm = HuggingFaceInferenceAPI(
-    model_name="gradientai/Llama-3-70B-Instruct-Gradient-1048k",
-    tokenizer_name="gradientai/Llama-3-70B-Instruct-Gradient-1048k",
+    model_name="tiiuae/falcon-11B",
+    tokenizer_name="tiiuae/falcon-11B",
     context_window=3000,
     token=os.getenv("HF_TOKEN"),
     max_new_tokens=512,