Update app.py

app.py

@@ -1,3 +1,13 @@
 import gradio as gr
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="meta-llama/Llama-2-7b-chat-hf")
+
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
+
 
 gr.load("models/meta-llama/Llama-2-7b-hf").launch()