# Load model directly
from transformers import AutoProcessor, AutoModelForTokenClassification
processor = AutoProcessor.from_pretrained("Ammar-alhaj-ali/LayoutLMv3-Fine-Tuning-FUNSD")
model = AutoModelForTokenClassification.from_pretrained("Ammar-alhaj-ali/LayoutLMv3-Fine-Tuning-FUNSD")Quick Links
layoutlmv3-finetuned-funsd
This model is a fine-tuned version of microsoft/layoutlmv3-base on the nielsr/funsd-layoutlmv3 dataset. It achieves the following results on the evaluation set:
- Loss: 1.038318
- Precision: 0.918177
- Recall: 0.930949
- F1: 0.924519
- Accuracy: 0.859979
- Downloads last month
- 5
Dataset used to train Ammar-alhaj-ali/LayoutLMv3-Fine-Tuning-FUNSD
Spaces using Ammar-alhaj-ali/LayoutLMv3-Fine-Tuning-FUNSD 2
Evaluation results
- Precision on nielsr/funsd-layoutlmv3self-reported0.918
- Recall on nielsr/funsd-layoutlmv3self-reported0.931
- F1 on nielsr/funsd-layoutlmv3self-reported0.925
- Accuracy on nielsr/funsd-layoutlmv3self-reported0.860
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Ammar-alhaj-ali/LayoutLMv3-Fine-Tuning-FUNSD")