Update app.py

app.py

@@ -61,8 +61,8 @@ templates = Jinja2Templates(directory="static")
 
 # Configure Llama index settings
 Settings.llm = HuggingFaceInferenceAPI(
-    model_name="meta-llama/Meta-Llama-3-8B-Instruct",
-    tokenizer_name="meta-llama/Meta-Llama-3-8B-Instruct",
+    model_name="HuggingFaceH4/zephyr-7b-beta",
+    tokenizer_name="HuggingFaceH4/zephyr-7b-beta",
     context_window=3000,
     token=os.getenv("HF_TOKEN"),
     max_new_tokens=512,