malayalam-bert-finetuned-ner

AksharaBalan/malayalam-bert-finetuned-ner

malayalam-bert-finetuned-ner is a token classification model from AksharaBalan. 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. --

Downloads · 30 days

1.9K

24% of all-time downloads

All-time downloads

7.9K

Public

Parameters

237M

2.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors948 MB · 99%

At a glance

Task: Token Classification
Library: transformers
License: cc-by-4.0
Model type: bert
Access: Public
Created: Mar 10, 2025
Updated: Mar 10, 2025
SHA: ba8ad85b

Try a prompt

Base models

l3cube-pune/malayalam-bert

Model card

From the Hugging Face model README

malayalam-bert-finetuned-ner

This model is a fine-tuned version of l3cube-pune/malayalam-bert on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3393

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-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.3455	1.0	2813	0.3711
0.323	2.0	5626	0.3377
0.2676	3.0	8439	0.3393

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

Task: Token Classification
Library: transformers
Type: bert
License: cc-by-4.0
Created: Mar 10, 2025
Updated: Mar 10, 2025