Update app.py

app.py

@@ -7,7 +7,8 @@ import spaces
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextIteratorStreamer
 
-subprocess.run('pip install transformers tokenizers flash-attn -U --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+subprocess.run('pip install -U transformers tokenizers', shell=True)
+subprocess.run('pip install -U flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
 MODEL_ID = "AtAndDev/marco-qwq-7B"
 CHAT_TEMPLATE = "ChatML"