Update app.py

app.py

@@ -4,7 +4,7 @@ import os
 import gradio as gr
 from threading import Thread
 from transformers import TextIteratorStreamer, AutoTokenizer, AutoModelForCausalLM
-import subprocess
+
 from PIL import Image
 from io import BytesIO
 import base64
@@ -22,7 +22,9 @@ def readb64(b64):
     return img
 
 
-subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+    # not sure why
+import subprocess
+subprocess.run('pip3 install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
 model_id = "vikhyatk/moondream2"
 revision = "2024-04-02"