Rtdl

This is a technical release, no changes in API. Also, check out our new paper ["On Embeddings for Numerical Features in Tabular Deep Learning"](https://arxiv.org/abs/2203.05556).

Changes
- minor documentation fix
- moved paper implementations to separate repositories

This is a technical update which was required for the release of our new paper ["On Embeddings for Numerical Features in Tabular Deep Learning"](https://github.com/Yura52/rtdl/tree/main/projects/num-embeddings). This version does not bring any functional changes to the `rtdl` library compared to the previous version (v0.0.10).

New features
- `rtdl.data.get_category_sizes`

Project
- some changes in the documentation reflecting the new structure of the repository

This is a hot-fix release after the big 0.0.8 release (see the [release notes](https://github.com/yandex-research/rtdl/releases/tag/v0.0.8) for 0.0.8):
- revert the breaking change in NumericalFeatureTokenizer accidentally introduced in 0.0.8
- minor documentation refinements

This release focuses on improving the documentation.

Documentation
- The following models and classes are now documented:
- `MLP`
- `ResNet`
- `FTTransformer`
- `MultiheadAttention`
- `NumericalFeatureTokenizer`
- `CategoricalFeatureTokenizer`
- `FeatureTokenizer`
- `CLSToken`
- Usability have been greatly improved:
- signatures are now highlighted
- added the "copy" button to code blocks
- permalink buttons (signature anchors) are now visible

Bug fixes
- `MultiheadAttention`: fix the crash when `bias=False`

Dependencies
- numpy >= 1.18
- torch >= 1.7

Project
- added spell checking for documentation
- sphinx was updated to 4.2.0
- flit was updated to 3.4.0

API changes
- remove `FlatEmbedding`

Project
- remove `bin`, `lib` and `output` from the PyPI package