Spaces:

prithivMLmods
/

Multimodal-OCR3

Running on Zero

prithivMLmods commited on Oct 17, 2025

Commit

f452786

verified ·

1 Parent(s): c417fc1

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -141,7 +141,7 @@ model_p = AutoModelForImageTextToText.from_pretrained(
     trust_remote_code=True,
     subfolder=SUBFOLDER_P,
     torch_dtype=torch.float16,
-    attn_implementation="flash_attention_2"
 ).to(device).eval()

     trust_remote_code=True,
     subfolder=SUBFOLDER_P,
     torch_dtype=torch.float16,
+    #attn_implementation="flash_attention_2"
 ).to(device).eval()