mbart-neutralization

CarlaLlavador/mbart-neutralization

mbart-neutralization is a machine learning model from CarlaLlavador. Use it for the machine learning task on the model card, and read the license before you ship it in a product. 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

23% of all-time downloads

All-time downloads

Public

Parameters

611M

7.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors2.4 GB · 99%

At a glance

Library: transformers
License: mit
Model type: mbart
Access: Public
Created: Mar 12, 2025
Updated: Mar 19, 2025
SHA: 895e6b19

Base models

facebook/mbart-large-50

Model card

From the Hugging Face model README

mbart-neutralization

This model is a fine-tuned version of facebook/mbart-large-50 on the dataset https://huggingface.co/datasets/somosnlp-hackathon-2022/neutral-es, a dataset for translating from "normal" Spanish to "inclusive" Spanish.. It achieves the following results on the evaluation set:

Loss: 0.0108
Bleu: 98.1542
Gen Len: 18.7396

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: 5.6e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	440	0.0250	95.7694	18.6458
0.2254	2.0	880	0.0108	98.1542	18.7396

Framework versions

Transformers 4.49.0
Pytorch 2.5.1+cu124
Datasets 3.3.2
Tokenizers 0.21.0

Library: transformers
Type: mbart
License: mit
Created: Mar 12, 2025
Updated: Mar 19, 2025