Downloads · 30 days
7
1% of all-time downloads
bert-base-ft-ner-xtreme-id
Sultannn/bert-base-ft-ner-xtreme-id
bert-base-ft-ner-xtreme-id is a token classification model from Sultannn. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
probably proofread and complete it, then remove this comment. --
All-time downloads
835
Public
Repo size
2.7 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.h5667 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Apr 21, 2022
- Updated
- Apr 22, 2022
- SHA
- a33bed03
Try a prompt
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
Sultannn/bert-base-ft-ner-xtreme-id
This model is a fine-tuned version of bert-base-multilingual-uncased on an xtreme PAN-X.id for NER downstream task.
Details of the downstream task (NER) - Dataset
| Dataset | # Examples |
|---|---|
| Train | 35 K |
| Validation | 5 K |
Metrics on evaluation set
| Metrics | Score |
|---|---|
| Accuracy | 97.18 |
| F1 | 93.26 |
| Precision | 92.36 |
| Recall | 94.18 |
Training hyperparameters
- Optimizer = AdamW
- LearningRate = 4e-5
- WeightDecay = 1e-2
- Warmup = 500
Example of usage
# pipeline example
from transformers import pipeline
model_checkpoint = "Sultannn/bert-base-ft-ner-xtreme-id"
token_classifier = pipeline(
"token-classification", model=model_checkpoint, aggregation_strategy="simple")
text = "nama saya Tono saya bekerja di Facebook dan tinggal di Jawa"
token_classifier(text)
Framework versions
- Transformers 4.18.0
- TensorFlow 2.8.0
- Datasets 2.1.0
- Tokenizers 0.12.1
Made with <span style="color: #e25555;">♥</span> in 🌏
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Languages
- id
- Created
- Apr 21, 2022
- Updated
- Apr 22, 2022