Instructions to use mbeukman/xlm-roberta-base-finetuned-amharic-finetuned-ner-swahili with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mbeukman/xlm-roberta-base-finetuned-amharic-finetuned-ner-swahili with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="mbeukman/xlm-roberta-base-finetuned-amharic-finetuned-ner-swahili")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("mbeukman/xlm-roberta-base-finetuned-amharic-finetuned-ner-swahili") model = AutoModelForTokenClassification.from_pretrained("mbeukman/xlm-roberta-base-finetuned-amharic-finetuned-ner-swahili", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| f1 = 0.866555462885738 | |
| loss = 0.23361517936721038 | |
| precision = 0.85233798195242 | |
| recall = 0.8812553011026294 | |
| report = precision recall f1-score support | |
| DATE 0.77 0.93 0.84 162 | |
| LOC 0.88 0.92 0.90 463 | |
| ORG 0.75 0.73 0.74 221 | |
| PER 0.93 0.91 0.92 333 | |
| micro avg 0.85 0.88 0.87 1179 | |
| macro avg 0.83 0.87 0.85 1179 | |
| weighted avg 0.85 0.88 0.87 1179 | |