Update README.md
Browse files
README.md
CHANGED
|
@@ -2,5 +2,6 @@ An image caption model [ViT-GPT2](https://huggingface.co/flax-community/vit-gpt2
|
|
| 2 |
|
| 3 |
Part of the [Huggingface JAX/Flax event](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/).
|
| 4 |
|
|
|
|
| 5 |
The pretained weights of both models are loaded, with a set of randomly initialized cross-attention weigths.
|
| 6 |
The model is trained on 65000 images from the COCO dataset for about 1500 steps, with the original english cpationis are translated to french for training purpose.
|
|
|
|
| 2 |
|
| 3 |
Part of the [Huggingface JAX/Flax event](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/).
|
| 4 |
|
| 5 |
+
The GPT2 model source code is modified so it can accept an encoder's output.
|
| 6 |
The pretained weights of both models are loaded, with a set of randomly initialized cross-attention weigths.
|
| 7 |
The model is trained on 65000 images from the COCO dataset for about 1500 steps, with the original english cpationis are translated to french for training purpose.
|