Instructions to use Kwan0/layoutlmv3-base-finetune-DocLayNet-100k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kwan0/layoutlmv3-base-finetune-DocLayNet-100k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Kwan0/layoutlmv3-base-finetune-DocLayNet-100k")# Load model directly from transformers import AutoProcessor, AutoModelForTokenClassification processor = AutoProcessor.from_pretrained("Kwan0/layoutlmv3-base-finetune-DocLayNet-100k") model = AutoModelForTokenClassification.from_pretrained("Kwan0/layoutlmv3-base-finetune-DocLayNet-100k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- ee1d7c665ddaa2a8e827e151c96b5c8515183f51f8e93e030a4f126494500c08
- Size of remote file:
- 504 MB
- SHA256:
- 070b9caa9ce6098cc858fb356271b0798eaaf92fed675b6bae5b842b930c3d9d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.