Tirth Patel

I believe the figure was first added by @rgommers [here](https://github.com/data-apis/array-api/commit/e2474ce03e6f60e52dd66c9390a8113ffd36a1b8) in [this PR](https://github.com/data-apis/array-api/pull/106).

Here's the [original document on lucidchart](https://lucid.app/lucidchart/e8d64501-0e22-495c-93ac-c47e4cd0aa01/edit?viewport_loc=173%2C329%2C1872%2C1027%2C0_0&invitationId=inv_eef9b0bb-b37c-4758-b666-a063458a8050).

I plan to add larger LLaMA presets in KerasNLP. No plans for Yi or Quen yet.

@innat Are you planning/volunteering to work on this or any of the components? I see you proposed #2319 which seems like a replication of the SWIN transformer of the Grounding...

This should theoretically be supported since we allow any tensors of shape `(..., H, W, C)`. I am guessing videos are just frames of images with shape `(B, NUM_FRAMES, H,...

I can see an argument for temporal consistency across frames when preprocessing but that seems like too much of a stretch from what KerasCV is designed to do. If we...

I don't have a strong opinion. At the first glance though, I'd be against adding this simply because you can always reshape the input tensors to make them work for...

Again, no strong opinion. If you have a diff, feel free to propose. It would be also nice to first identify the layers where videos need to be treated differently....

I feel like `seed` would be a better choice than `rng`. It's more commonly used and is more user-friendly since we allow passing seeds. Unlike `seed`, it might not occur...

Hi @doug1e, I think tensorflowjs is not able to load the weights saved by Keras 3. Instead of saving the model to `.keras`, you can try saving it to TF...