Downloads · 30 days
4
3% of all-time downloads
mBART-large-50-si-spelling-v4-multi
SPEAK-PP/mBART-large-50-si-spelling-v4-multi
mBART-large-50-si-spelling-v4-multi is a machine learning model from SPEAK-PP. 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. --
All-time downloads
153
Public
Parameters
611M
29.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.9 GB · 50%
At a glance
- Library
- transformers
- License
- mit
- Model type
- mbart
- Access
- Public
- Created
- Mar 4, 2026
- Updated
- Mar 4, 2026
- SHA
- 3d9d389d
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. -->
SPEAK-PP/mBART-large-50-si-spelling-v4-multi
This model is a fine-tuned version of facebook/mbart-large-50 on the SPEAK-PP/openslr-sinhala-spelling-correction-prediction-reference dataset. It achieves the following results on the evaluation set:
- Loss: 0.1938
- Bleu: 1.0688
- Exact Match: 0.0
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Exact Match |
|---|---|---|---|---|---|
| 0.1836 | 1.0 | 193 | 0.1698 | 1.1145 | 0.0026 |
| 0.1324 | 2.0 | 386 | 0.1590 | 0.5387 | 0.0 |
| 0.0806 | 3.0 | 579 | 0.1713 | 1.0416 | 0.0026 |
| 0.05 | 4.0 | 772 | 0.1938 | 1.0688 | 0.0 |
Framework versions
- Transformers 4.55.0
- Pytorch 2.9.0.dev20250821+rocm7.0.0.git125803b7
- Datasets 4.0.0
- Tokenizers 0.21.4
- Library
- transformers
- Type
- mbart
- License
- mit
- Languages
- si
- Created
- Mar 4, 2026
- Updated
- Mar 4, 2026