Downloads · 30 days
11
20% of all-time downloads
nb-bert-norne-wikiann-ner
thivy/nb-bert-norne-wikiann-ner
nb-bert-norne-wikiann-ner is a token classification model from thivy. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as cc-by-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
56
Public
Parameters
177M
9.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors709 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- cc-by-4.0
- Model type
- bert
- Access
- Public
- Created
- Dec 22, 2025
- Updated
- Dec 24, 2025
- SHA
- 8540a6ea
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
nb-bert-norne-wikiann-ner
This model is a fine-tuned version of NbAiLab/nb-bert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1102
- Precision: 0.9208
- Recall: 0.9298
- F1: 0.9253
- Accuracy: 0.9843
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0583 | 1.0 | 6234 | 0.1042 | 0.8931 | 0.9049 | 0.8989 | 0.9787 |
| 0.0469 | 2.0 | 12468 | 0.0923 | 0.9047 | 0.9198 | 0.9122 | 0.9813 |
| 0.0323 | 3.0 | 18702 | 0.0836 | 0.9176 | 0.9246 | 0.9211 | 0.9830 |
| 0.0262 | 4.0 | 24936 | 0.0883 | 0.9197 | 0.9281 | 0.9239 | 0.9838 |
| 0.0223 | 5.0 | 31170 | 0.0940 | 0.9197 | 0.9297 | 0.9246 | 0.9844 |
| 0.0201 | 6.0 | 37404 | 0.1005 | 0.9207 | 0.9288 | 0.9247 | 0.9842 |
| 0.0082 | 7.0 | 43638 | 0.1102 | 0.9208 | 0.9298 | 0.9253 | 0.9843 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.1
- Datasets 4.4.1
- Tokenizers 0.22.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- cc-by-4.0
- Created
- Dec 22, 2025
- Updated
- Dec 24, 2025