Update app.py

app.py

@@ -1,10 +1,12 @@
 #!/usr/bin/env python3
-# sloppy header
+
+
 
 import os, json, time, random, threading, logging
 from datetime import datetime, timezone
 import torch; torch.set_num_threads(os.cpu_count()); torch.set_num_interop_threads(os.cpu_count())
 import gradio as gr
+
 from transformers import AutoTokenizer, AutoModelForCausalLM
 from gradio.themes import Dark
 
@@ -12,6 +14,7 @@ MODEL_NAME = "meta-llama/Llama-3.1-8B-Instruct"
 PROMPTS_PATH = "full_prompts.json"
 STATE_PATH = "current_state.json"
 DATA_PATH = "data.json"
+
 TOKENS_PER_PROMPT = 2048
 SECS_PER_TOKEN = 15
 TEMP = 0.9; TOP_P = 0.95; MAX_CTX = 8192