Update app.py

app.py

@@ -13,8 +13,10 @@ load_dotenv()
 
 # Configure the Llama index settings
 Settings.llm = HuggingFaceInferenceAPI(
-    model_name = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B"),
-    tokenizer_name = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B"),
+    #model_name = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B"),
+    #tokenizer_name = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B"),
+    tokenizer_name = AutoTokenizer.from_pretrained("gradientai/Llama-3-8B-Instruct-Gradient-1048k"),
+    model_name = AutoModelForCausalLM.from_pretrained("gradientai/Llama-3-8B-Instruct-Gradient-1048k"),
     context_window=3900,
     token=os.getenv("HF_TOKEN"),
     max_new_tokens=1000,