Update app.py

app.py

@@ -12,9 +12,9 @@ load_dotenv()
 
 # Configure the Llama index settings
 Settings.llm = HuggingFaceInferenceAPI(
-    model_name="meta-llama/Meta-Llama-3-8B-Instruct",
-    tokenizer_name="meta-llama/Meta-Llama-3-8B-Instruct",
-    context_window=4000,
+    model_name="meta-llama/Meta-Llama-3-8B",
+    tokenizer_name="meta-llama/Meta-Llama-3-8B",
+    context_window=3000,
     token=os.getenv("HF_TOKEN"),
     max_new_tokens=2048,
     generate_kwargs={"temperature": 0.1},