Truegrad

* feat(nn.functional): allow parameters in more `truegrad.nn.functional` ops
* fix(functional): allow odd shapes in `truegrad.functional.einsum`'s backward
* feat(utils): allow the combination of `truegrad.nn` with `truegrad.utils.patch_model`
* fix(TGAdamW): improve stability

Together, these features allow performant usage of off-the-shelf HuggingFace Transformers using `truegrad.utils.patch_torch`.

* Feature: Patch `torch` and `torch.nn.functional` in `truegrad.utils.patch_torch`
* Feature: Add chunk, split and transpose to `truegrad.functional`
* Fix: publicly expose `truegrad.nn.functional`
* Fix: use patched chunk, split and transpose functions in `truegrad.nn.functional.multi_head_attention_forward` (closes 1)

* Add `truegrad.nn.functional`
* Extend `truegrad.nn`
* Add `truegrad.utils.patch_torch`
* Add `truegrad.functional.TrueGradTensor` to store `sum_grad_squared` (-> fixed `truegrad.functional.reshape`)

* Add BackPack as possible backend
* default_to_adam option for TGAdamW
* rename square_grad to sum_grad_squared