Hugging Face's logo

Spaces:
prithivMLmods
/
Multimodal-OCR
Running on Zero

App Files Community
prithivMLmods commited on
Commit
e440671
·
verified ·
1 Parent(s): 7f693e5

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -65,7 +65,7 @@ def downsample_video(video_path):
65
 
66
  # Model and Processor Setup
67
  # Qwen2VL OCR (default branch)
68
- QV_MODEL_ID = "prithivMLmods/Qwen2-VL-OCR-2B-Instruct"
69
  qwen_processor = AutoProcessor.from_pretrained(QV_MODEL_ID, trust_remote_code=True)
70
  qwen_model = Qwen2VLForConditionalGeneration.from_pretrained(
71
  QV_MODEL_ID,
 
65
 
66
  # Model and Processor Setup
67
  # Qwen2VL OCR (default branch)
68
+ QV_MODEL_ID = "prithivMLmods/Qwen2-VL-OCR-2B-Instruct" #[or] prithivMLmods/Qwen2-VL-OCR2-2B-Instruct
69
  qwen_processor = AutoProcessor.from_pretrained(QV_MODEL_ID, trust_remote_code=True)
70
  qwen_model = Qwen2VLForConditionalGeneration.from_pretrained(
71
  QV_MODEL_ID,