nanoLLaVA

Running on Zero

qnguyen3 commited on Apr 8

Commit

08bc998

•

1 Parent(s): 95306c4

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -6,6 +6,8 @@ import time
 from PIL import Image
 import torch
 import spaces
 tokenizer = AutoTokenizer.from_pretrained(
     'qnguyen3/nanoLLaVA',

 from PIL import Image
 import torch
 import spaces
+import subprocess
+subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 tokenizer = AutoTokenizer.from_pretrained(
     'qnguyen3/nanoLLaVA',