Downloads · 30 days
2
3% of all-time downloads
paligemma2_vizwiz_gqa
ebrukilic/paligemma2_vizwiz_gqa
paligemma2_vizwiz_gqa is a text generation model from ebrukilic. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as gemma.
should probably proofread and complete it, then remove this comment. --
All-time downloads
62
Public
Repo size
47.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors47.6 MB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- gemma
- Access
- Public
- Created
- Dec 31, 2025
- Updated
- Dec 31, 2025
- SHA
- 0582388d
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. -->
paligemma2_vizwiz_gqa
This model is a fine-tuned version of ebrukilic/paligemma2_vizwiz_ft2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4691
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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 |
|---|---|---|---|
| 0.8199 | 0.0288 | 200 | 0.6891 |
| 0.6335 | 0.0575 | 400 | 0.6061 |
| 0.5961 | 0.0863 | 600 | 0.5755 |
| 0.5773 | 0.1150 | 800 | 0.5565 |
| 0.5723 | 0.1438 | 1000 | 0.5471 |
| 0.5853 | 0.1725 | 1200 | 0.5325 |
| 0.5973 | 0.2013 | 1400 | 0.5301 |
| 0.5319 | 0.2300 | 1600 | 0.5167 |
| 0.525 | 0.2588 | 1800 | 0.5178 |
| 0.542 | 0.2875 | 2000 | 0.5051 |
| 0.5971 | 0.3163 | 2200 | 0.5006 |
| 0.5757 | 0.3450 | 2400 | 0.5005 |
| 0.5026 | 0.3738 | 2600 | 0.4914 |
| 0.5441 | 0.4025 | 2800 | 0.4802 |
| 0.5473 | 0.4313 | 3000 | 0.4861 |
| 0.4936 | 0.4600 | 3200 | 0.4880 |
| 0.4442 | 0.4888 | 3400 | 0.4821 |
| 0.5176 | 0.5175 | 3600 | 0.4668 |
| 0.4546 | 0.5463 | 3800 | 0.4720 |
| 0.481 | 0.5750 | 4000 | 0.4726 |
| 0.4701 | 0.6038 | 4200 | 0.4693 |
| 0.5143 | 0.6325 | 4400 | 0.4691 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.4.2
- Tokenizers 0.22.1
- Task
- Text Generation
- Library
- peft
- License
- gemma
- Created
- Dec 31, 2025
- Updated
- Dec 31, 2025