Downloads · 30 days
23
20% of all-time downloads
blip-gqa-ft-trial3
phucd/blip-gqa-ft-trial3
blip-gqa-ft-trial3 is a visual question answering model from phucd. Use it for the visual question answering 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
114
Public
Parameters
3.7B
44.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors15 GB · 100%
At a glance
- Task
- Visual Question Answering
- Library
- transformers
- License
- mit
- Model type
- blip-2
- Access
- Public
- Created
- May 3, 2025
- Updated
- May 3, 2025
- SHA
- 22b563b9
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. -->
blip-gqa-ft-trial3
This model is a fine-tuned version of Salesforce/blip2-opt-2.7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7298
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.917 | 1.0 | 313 | 1.9330 |
| 1.6347 | 2.0 | 626 | 1.8037 |
| 1.6861 | 2.992 | 936 | 1.7298 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu121
- Datasets 3.5.0
- Tokenizers 0.21.1
- Task
- Visual Question Answering
- Library
- transformers
- Type
- blip-2
- License
- mit
- Created
- May 3, 2025
- Updated
- May 3, 2025