Downloads · 30 days
20
4% of all-time downloads
Swin2-GTP2_art-caption
AterMors/Swin2-GTP2_art-caption
Swin2-GTP2_art-caption is a image-to-text model from AterMors. Use it when you need a caption or text from an image. It is set up for transformers. The card lists the license as apache-2.0.
Image Captioning Model created with VisionEncoderDecoderModel architecture using "microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft" as imageencoder and "openai/gpt2" as textdecoder. It has been trained on…
All-time downloads
562
Public
Parameters
240M
975 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors962 MB · 98%
At a glance
- Task
- Image-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- vision-encoder-decoder
- Access
- Public
- Created
- Jul 15, 2024
- Updated
- Jul 15, 2024
- SHA
- 293dae6c
Base models
Datasets
Model card
From the Hugging Face model README
Image Captioning Model created with VisionEncoderDecoderModel architecture using "microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft" as image_encoder and "openai/gpt2" as text_decoder. It has been trained on a variant of the WikiArt dataset that can be found at "AterMors/wikiart_recaption".
- Task
- Image-to-Text
- Library
- transformers
- Type
- vision-encoder-decoder
- License
- apache-2.0
- Languages
- en
- Created
- Jul 15, 2024
- Updated
- Jul 15, 2024