Update app.py

app.py

@@ -1,10 +1,12 @@
 import gradio as gr
 import spaces 
 import transformers 
-from transformers import AutoTokenizer,AutoModelForCausalLM
 from transformers import pipeline 
 import torch 
 import os 
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+
 
 api_token = os.environ.get("APIKEY")
 
@@ -12,7 +14,6 @@ api_token = os.environ.get("APIKEY")
 
 @spaces.GPU(duration=240)
 # Load model directly
-from transformers import AutoTokenizer, AutoModelForCausalLM
 
 tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
 model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct",token=api_token)