Instructions to use fktime/NuNER-multilingual-v0.1-ai4p with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fktime/NuNER-multilingual-v0.1-ai4p with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="fktime/NuNER-multilingual-v0.1-ai4p")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("fktime/NuNER-multilingual-v0.1-ai4p") model = AutoModelForTokenClassification.from_pretrained("fktime/NuNER-multilingual-v0.1-ai4p") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Overall Metrics: Overall Precision: 85.48% Overall Recall: 89.07% Overall F1 Score: 87.24% Overall Accuracy: 96.05%
High-Performing Entities: ACCOUNTNAME: F1 score of 98.85% ACCOUNTNUMBER: F1 score of 94.71% AGE: F1 score of 97.25% EMAIL: F1 score of 99.18% ETHEREUMADDRESS: F1 score of 98.05% NEARBYGPSCOORDINATE: F1 score of 99.55% PHONEIMEI: F1 score of 98.40% PHONENUMBER: F1 score of 97.17%
Entities That Need Improvement: IP: F1 score of 0.0% (no samples predicted) LITECOINADDRESS: F1 score of 0.0% MASKEDNUMBER: F1 score of 9.98%
Numeric Entities: Entities like AGE and PHONEIMEI fall under this category!
Legal Entities: COMPANYNAME: F1 score of 95.99% JOBTITLE: F1 score of 97.11% STATE: F1 score of 93.24%
- Downloads last month
- 2