langtok

emmabedna/langtok

langtok is a token classification model from emmabedna. 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.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

17% of all-time downloads

All-time downloads

Public

Parameters

177M

5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors709 MB · 99%

At a glance

Task: Token Classification
Library: transformers
License: apache-2.0
Model type: bert
Access: Public
Created: Jan 24, 2025
Updated: Jan 24, 2025
SHA: 59cd0b7b

Try a prompt

Base models

Model card

From the Hugging Face model README

bert-base-multilingual-cased-finetuned-langtok_new

This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0399
Precision: 0.8690
Recall: 0.8859
F1: 0.8774
Accuracy: 0.9898

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0693	1.0	1137	0.0519	0.8315	0.8521	0.8417	0.9859
0.0365	2.0	2274	0.0432	0.8616	0.8808	0.8711	0.9890
0.0205	3.0	3411	0.0399	0.8690	0.8859	0.8774	0.9898

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1

Task: Token Classification
Library: transformers
Type: bert
License: apache-2.0
Created: Jan 24, 2025
Updated: Jan 24, 2025