How to use vikp/layout_segmenter with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="vikp/layout_segmenter")
# Load model directly from transformers import AutoProcessor, AutoModelForTokenClassification processor = AutoProcessor.from_pretrained("vikp/layout_segmenter") model = AutoModelForTokenClassification.from_pretrained("vikp/layout_segmenter", device_map="auto")
https://huggingface.co/vikp/layout_segmenter/resolve/refs%2Fpr%2F3/tokenizer.json
hf download hf://vikp/layout_segmenter@refs/pr/3/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/vikp/layout_segmenter/resolve/refs%2Fpr%2F3/tokenizer.json
