Downloads · 30 days
3
3% of all-time downloads
_Arabic_nougat_AHR_jawi
bustamiyusoef/_Arabic_nougat_AHR_jawi
_Arabic_nougat_AHR_jawi is a image-text-to-text model from bustamiyusoef. Use it for the image-text-to-text 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 gpl-3.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
102
Public
Parameters
349M
698 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors698 MB · 99%
Parameter types
How the weights are stored.
BF16349M · 100%
Try a prompt
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. -->
_Arabic_nougat_AHR_jawi
This model is a fine-tuned version of bustamiyusoef/_Arabic_nougat_AHR on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1466
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 6
- total_train_batch_size: 48
- 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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1571 | 1.0 | 84 | 0.1905 |
| 0.765 | 2.0 | 168 | 0.1569 |
| 0.496 | 3.0 | 252 | 0.1441 |
| 0.4405 | 4.0 | 336 | 0.1385 |
| 0.5234 | 5.0 | 420 | 0.1353 |
| 0.2397 | 6.0 | 504 | 0.1368 |
| 0.2452 | 7.0 | 588 | 0.1400 |
| 0.1811 | 8.0 | 672 | 0.1419 |
| 0.1596 | 9.0 | 756 | 0.1466 |
| 0.1809 | 10.0 | 840 | 0.1438 |
| 0.1372 | 11.0 | 924 | 0.1451 |
| 0.1614 | 12.0 | 1008 | 0.1463 |
| 0.0941 | 13.0 | 1092 | 0.1463 |
| 0.1985 | 14.0 | 1176 | 0.1468 |
| 0.1548 | 14.828 | 1245 | 0.1466 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- vision-encoder-decoder
- License
- gpl-3.0
- Created
- Jan 16, 2025
- Updated
- Jan 16, 2025