Update app.py

app.py

@@ -2,6 +2,9 @@ import gradio as gr
 import torch
 from transformers import AutoTokenizer, LlamaForCausalLM
 import spaces
+import subprocess
+subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+
 
 # Initialize model and tokenizer
 model_id = 'akjindal53244/Llama-3.1-Storm-8B'