Downloads · 30 days
12
18% of all-time downloads
DonutInvoiceCzechV012
TomasFAV/DonutInvoiceCzechV012
DonutInvoiceCzechV012 is a image-text-to-text model from TomasFAV. 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 mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
67
Public
Parameters
201M
8.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors806 MB · 99%
Parameter types
How the weights are stored.
F32201M · 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. -->
DonutInvoiceCzechV012
This model is a fine-tuned version of TomasFAV/DonutInvoiceCzechV01 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3897
- Accuracy: 0.8944
- F1: 0.8792
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: 9e-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.1209 | 1.0 | 230 | 0.3804 | 0.8237 | 0.8296 |
| 0.0876 | 2.0 | 460 | 0.4660 | 0.8350 | 0.8330 |
| 0.0427 | 3.0 | 690 | 0.4718 | 0.8289 | 0.8407 |
| 0.0236 | 4.0 | 920 | 0.3743 | 0.8712 | 0.8701 |
| 0.0127 | 5.0 | 1150 | 0.4255 | 0.8424 | 0.8405 |
| 0.0115 | 6.0 | 1380 | 0.3897 | 0.8944 | 0.8792 |
| 0.0075 | 7.0 | 1610 | 0.4155 | 0.8803 | 0.8711 |
| 0.0062 | 8.0 | 1840 | 0.4623 | 0.8722 | 0.8650 |
| 0.0021 | 9.0 | 2070 | 0.4560 | 0.8808 | 0.8702 |
| 0.0033 | 10.0 | 2300 | 0.4488 | 0.8784 | 0.8671 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- vision-encoder-decoder
- License
- mit
- Created
- Apr 18, 2026
- Updated
- Apr 19, 2026