bert-ner-demo

Riprobot/bert-ner-demo

bert-ner-demo is a token classification model from Riprobot. 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. --

Downloads · 30 days

127

92% of all-time downloads

All-time downloads

138

Public

Parameters

33.2M

5.2 GB on disk

Likes

Public

Hugging Face

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: Oct 4, 2025
Updated: Oct 4, 2025
SHA: 55a261aa

Try a prompt

Base models

BAAI/bge-small-en-v1.5

Model card

From the Hugging Face model README

bert-ner-demo

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: 0.0849
Precision: 0.9293
Recall: 0.9427
F1: 0.9360
Accuracy: 0.9823

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.5099	1.0	625	0.1821	0.8268	0.8526	0.8395	0.9612
0.1799	2.0	1250	0.1148	0.8821	0.9130	0.8973	0.9748
0.1204	3.0	1875	0.0881	0.9042	0.9355	0.9196	0.9788
0.0656	4.0	2500	0.0839	0.9061	0.9350	0.9204	0.9795
0.0542	5.0	3125	0.0802	0.9185	0.9377	0.9280	0.9805
0.0433	6.0	3750	0.0801	0.9267	0.9393	0.9330	0.9813
0.0375	7.0	4375	0.0808	0.9252	0.9437	0.9344	0.9818
0.0284	8.0	5000	0.0794	0.9317	0.9434	0.9375	0.9826
0.0246	9.0	5625	0.0849	0.9260	0.9401	0.9330	0.9810
0.0209	10.0	6250	0.0861	0.9258	0.9433	0.9344	0.9816
0.0201	11.0	6875	0.0824	0.9304	0.9435	0.9369	0.9825
0.0164	12.0	7500	0.0849	0.9293	0.9427	0.9360	0.9823

Framework versions

Transformers 4.56.2
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

Task: Token Classification
Library: transformers
Type: bert
License: mit
Created: Oct 4, 2025
Updated: Oct 4, 2025