xlstm-config: temporarily introduce new hidden_size parameter

readme: include some new logo :-)

figure: add some new logo :p

readme: update information about final xLSTM model (one epoch over corpus)

figure: add updated loss curve for training

model: add newly trained xLSTM model (with grad clipping)

readme: cleanup configuration example

readme: mention currently missing grad norm

readme: mention Tristan

readme: mention Tristan

readme: add more training details

readme: add example usage

config: fix it

xlstm: add configuration and modeling (own one)

readme: mention uploaded checkpoint

tokenizer: add config and vocab

model: add generation confgi

model: add config and trained xLSTM model

figure: add training loss overview

readme: update

readme: finalize training section

metrics: add final logs after 2 epochs

model: add training log

model: add best model

readme: minor tweaks

readme: add initial version

initial commit