How to use cortex-ai-nova/NOVA-OCR2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="cortex-ai-nova/NOVA-OCR2", trust_remote_code=True)
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("cortex-ai-nova/NOVA-OCR2", trust_remote_code=True, device_map="auto")
https://huggingface.co/cortex-ai-nova/NOVA-OCR2/resolve/main/tokenizer.json
hf download hf://cortex-ai-nova/NOVA-OCR2/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/cortex-ai-nova/NOVA-OCR2/resolve/main/tokenizer.json
