Downloads · 30 days
4
2% of all-time downloads
NuNER-multilingual-v0.1-ai4p
fktime/NuNER-multilingual-v0.1-ai4p
NuNER-multilingual-v0.1-ai4p is a token classification model from fktime. Use it when you need labels on individual words, such as names. It is set up for transformers.
Overall Metrics: Overall Precision: 85.48% Overall Recall: 89.07% Overall F1 Score: 87.24% Overall Accuracy: 96.05%
All-time downloads
244
Public
Parameters
177M
2.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1.4 GB · 67%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- May 8, 2024
- Updated
- May 8, 2024
- SHA
- c837053f
Try a prompt
Model card
From the Hugging Face model README
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%
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- May 8, 2024
- Updated
- May 8, 2024