File size: 850 Bytes
2f35862 3ea1ff8 ef6a4ab ea6132e ef6a4ab 2f35862 |
1 2 3 4 5 6 7 8 9 10 11 |
**🖼️ When ViT meets GPT-2 📝**
An image captioning model [ViT-GPT2](https://huggingface.co/flax-community/vit-gpt2/tree/main) by combining the ViT model and a French GPT2 model.
Part of the [Huggingface JAX/Flax event](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/).
The GPT2 model source code is modified so it can accept an encoder's output.
The pretained weights of both models are loaded, with a set of randomly initialized cross-attention weigths.
The model is trained on 65000 images from the COCO dataset for about 1500 steps (batch\_size=256), with the original English cpationis being translated to French for training purpose.
A HuggingFace Space demo for this model: [🖼️ French Image Captioning Demo 📝](https://huggingface.co/spaces/flax-community/image-caption-french) |