Update app.py

app.py

@@ -2,7 +2,8 @@ import spaces
 import gradio as gr
 from cartesia_pytorch import ReneLMHeadModel
 from transformers import AutoTokenizer
-
+import subprocess
+subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 # Load model and tokenizer
 model = ReneLMHeadModel.from_pretrained("cartesia-ai/Rene-v0.1-1.3b-pytorch").half().cuda()
 tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-1B-hf")