Rtdl

New features
- `CLSToken` (old name: "AppendCLSToken"): add `expand` method for easy construction of batches of [CLS]-tokens

Bug fixes
- `FTTransformer`: the `make_baseline` method now properly constructs an instance

API changes
- `FTTransformer`: the `ffn_d_intermidiate` argument was renamed to a more conventional `ffn_d_hidden`
- `FTTransformer`: the `normalization` argument was split into three arguments: `attention_normalization`, `ffn_normalization`, `head_normalization`
- `ResNet`: the `d_intermidiate` argument was renamed to a more conventional `d_hidden`
- `AppendCLSToken`: renamed to `CLSToken`

Documentation improvements
- `CLSToken`
- `MLP.make_baseline`

Project
- add tests with CUDA
- remove the `.vscode` directory from the repository

API Changes:
- `MLP.make_baseline` is now more user-friendly and accepts a single `d_layers` argument instead of four (`d_first`, `d_intermidiate`, `d_last`, `n_blocks`)

Fixes
- make `CategoricalFeatureTokenizer` compatible with `.to(device)`

API Changes
- `ResNet` & `ResNet.Block`: the `d` parameter was renamed to `d_main`

Fixes
- minor fix in the comments in `examples/rtdl.ipynb`

Project
- add [tests](https://github.com/yandex-research/rtdl/blob/main/rtdl/tests/test_vs_paper.py) that validate that the models in `rtdl` are literally the same as in the implementation of the paper