Text Classification
Transformers
ONNX
Safetensors
German
xlm-roberta
job-classification
german
taxonomy-main
text-embeddings-inference
Instructions to use Ashybalka/xlm-roberta-taxonomy-main-de with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ashybalka/xlm-roberta-taxonomy-main-de with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Ashybalka/xlm-roberta-taxonomy-main-de")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Ashybalka/xlm-roberta-taxonomy-main-de") model = AutoModelForSequenceClassification.from_pretrained("Ashybalka/xlm-roberta-taxonomy-main-de", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| precision recall f1-score support | |
| Administration & Office 0.757 0.652 0.700 244 | |
| Construction & Building 0.607 0.733 0.664 116 | |
| Design & Creative 0.629 0.759 0.688 29 | |
| Education & Teaching 0.645 0.778 0.705 63 | |
| Engineering 0.776 0.745 0.760 474 | |
| Finance, Accounting & Controlling 0.754 0.772 0.763 254 | |
| General Management & Consulting 0.649 0.732 0.688 149 | |
| Healthcare & Medical 0.847 0.878 0.862 221 | |
| Hospitality, Gastronomy & Tourism 0.823 0.868 0.845 91 | |
| Human Resources 0.590 0.821 0.687 28 | |
| IT & Software 0.861 0.868 0.865 500 | |
| Insurance & Real Estate 0.683 0.887 0.772 80 | |
| Legal 0.600 0.667 0.632 18 | |
| Logistics, Transport & Warehouse 0.805 0.910 0.854 100 | |
| Marketing, Communications & PR 0.700 0.667 0.683 42 | |
| Production & Manufacturing 0.626 0.635 0.630 192 | |
| Public Sector, Security & Defense 0.720 0.805 0.760 118 | |
| Sales & Business Development 0.927 0.844 0.884 500 | |
| Science & Research 0.733 0.688 0.710 32 | |
| Skilled Trades & Crafts 0.833 0.778 0.805 500 | |
| Social Work & Care 0.844 0.756 0.797 164 | |
| accuracy 0.786 3915 | |
| macro avg 0.734 0.773 0.750 3915 | |
| weighted avg 0.792 0.786 0.788 3915 | |