Update app.py

app.py

@@ -8,6 +8,9 @@ from PIL import Image
 from transformers import AutoProcessor, AutoModelForCausalLM
 from transformers import TextIteratorStreamer
 
+import subprocess
+subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+
 PLACEHOLDER = """
 <div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
    <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">microsoft/Phi-3-vision-128k-instruct</h1>
@@ -17,6 +20,8 @@ user_prompt = '<|user|>\n'
 assistant_prompt = '<|assistant|>\n'
 prompt_suffix = "<|end|>\n"
 
+
+
 model_id = "microsoft/Phi-3-vision-128k-instruct"
 
 processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)