Update app.py

app.py

@@ -6,8 +6,7 @@ import spaces
 import os
 
 
-# Install flash-attn
-subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+
 # Initialize the model pipeline
 generator = pipeline('text-generation', model='hydra-project/ChatHercules-2.5-Mistral-7B', torch_dtype=torch.bfloat16)
 @spaces.GPU