Downloads · 30 days
4
7% of all-time downloads
bge-small-ner
akapesok/bge-small-ner
bge-small-ner is a token classification model from akapesok. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
58
Public
Parameters
33.2M
266 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors133 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Apr 23, 2026
- Updated
- Apr 24, 2026
- SHA
- b28387c3
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. -->
bge-small-ner
This model is a fine-tuned version of BAAI/bge-small-en-v1.5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0786
- Precision: 0.9227
- Recall: 0.9226
- F1: 0.9227
- Accuracy: 0.9822
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1348 | 1.0 | 625 | 0.1328 | 0.8658 | 0.8466 | 0.8483 | 0.9705 |
| 0.0813 | 2.0 | 1250 | 0.0947 | 0.9056 | 0.8972 | 0.9006 | 0.9780 |
| 0.0851 | 3.0 | 1875 | 0.0826 | 0.9026 | 0.9170 | 0.9096 | 0.9791 |
| 0.0469 | 4.0 | 2500 | 0.0791 | 0.9157 | 0.9192 | 0.9173 | 0.9804 |
| 0.0265 | 5.0 | 3125 | 0.0797 | 0.9166 | 0.9194 | 0.9180 | 0.9811 |
| 0.0334 | 6.0 | 3750 | 0.0767 | 0.9245 | 0.9209 | 0.9226 | 0.9822 |
| 0.0272 | 7.0 | 4375 | 0.0766 | 0.9205 | 0.9232 | 0.9218 | 0.9819 |
| 0.0150 | 8.0 | 5000 | 0.0779 | 0.9267 | 0.9193 | 0.9229 | 0.9823 |
| 0.0248 | 9.0 | 5625 | 0.0782 | 0.9200 | 0.9228 | 0.9214 | 0.9819 |
| 0.0262 | 10.0 | 6250 | 0.0786 | 0.9227 | 0.9226 | 0.9227 | 0.9822 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- mit
- Created
- Apr 23, 2026
- Updated
- Apr 24, 2026