Chen Chen
Chen Chen
Can the author confirm how the recall is implemented for both text to image and image to text given there are 5 captions per image?
Could you share more details of regex used in Dependency Parsing for each language?
https://github.com/huggingface/diffusers/blob/f4fc75035f2d567dfe00fc6b8671ecd38dd144b2/src/diffusers/schedulers/scheduling_dpmsolver_multistep_flax.py#L164 Apparently, `q` in [jnp.percentile](https://jax.readthedocs.io/en/latest/_autosummary/jax.numpy.percentile.html) should between [0, 100] instead of [0, 1] as in torch.