Downloads · 30 days
15
2% of all-time downloads
ViT-GPT2-Image-Captioning
mo-thecreator/ViT-GPT2-Image-Captioning
ViT-GPT2-Image-Captioning is a image-to-text model from mo-thecreator. Use it when you need a caption or text from an image. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
917
Public
Parameters
239M
1.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors957 MB · 100%
At a glance
- Task
- Image-to-Text
- Library
- transformers
- Model type
- vision-encoder-decoder
- Access
- Public
- Created
- Sep 30, 2024
- Updated
- Oct 7, 2024
- SHA
- 73fc76f5
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. -->
ViT-GPT2
This model is a fine-tuned version of motheecreator/ViT-GPT2-Image_Captioning_model on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.125337
- Rouge2 Precision: None
- Rouge2 Recall: None
- Rouge2 Fmeasure: 0.155
- Bleu: 9.7054
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: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure | Bleu |
|---|---|---|---|---|---|---|---|
| 2.1537 | 0.9993 | 1171 | 2.13666 | None | None | 0.1531 | 9.4673 |
| 2.0434 | 1.9985 | 2342 | 2.125337 | None | None | 0.155 | 9.7054 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 3.0.0
- Tokenizers 0.19.1
- Task
- Image-to-Text
- Library
- transformers
- Type
- vision-encoder-decoder
- Created
- Sep 30, 2024
- Updated
- Oct 7, 2024