Downloads · 30 days
92
51% of all-time downloads
slovakbert-skquad-qa
lukasjanek/slovakbert-skquad-qa
slovakbert-skquad-qa is a question answering model from lukasjanek. Use it when the input is a question plus a passage. 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
179
Public
Parameters
124M
496 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors496 MB · 99%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Mar 9, 2026
- Updated
- Mar 9, 2026
- SHA
- 1dd99149
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. -->
slovakbert-skquad-qa
This model is a fine-tuned version of gerulata/slovakbert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7027
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2782 | 1.0 | 1188 | 1.3700 |
| 0.8873 | 2.0 | 2376 | 1.3412 |
| 0.9179 | 3.0 | 3564 | 1.4290 |
| 0.5890 | 4.0 | 4752 | 1.5141 |
| 0.5666 | 5.0 | 5940 | 1.7027 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Task
- Question Answering
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- Mar 9, 2026
- Updated
- Mar 9, 2026