Xlm Roberta Base Finetuned Panx De
German token classification model fine-tuned on the xtreme dataset based on XLM-RoBERTa-base
Downloads 14
Release Time : 4/10/2022
Model Overview
This model is optimized for German text token classification tasks, based on the XLM-RoBERTa-base architecture and fine-tuned on the PAN-X.de dataset, suitable for tasks such as named entity recognition.
Model Features
Multilingual Support
Based on the XLM-RoBERTa architecture, capable of processing multilingual text
High-Precision Token Classification
Achieves an F1 score of 0.859 on the PAN-X.de dataset
Transfer Learning Optimization
Adapted for specific token classification tasks through fine-tuning of pre-trained models
Model Capabilities
German Text Token Classification
Named Entity Recognition
Sequence Labeling
Use Cases
Natural Language Processing
German Named Entity Recognition
Identify entities such as person names, place names, and organization names in German text
F1 score 0.859
Text Information Extraction
Extract structured information from German documents
Featured Recommended AI Models
Š 2025AIbase