Update README.md

Update README.md

Update README.md

Upload from scratch training of gradual/cyclic ppo-kl

Update README.md

Update README.md

Update README.md

Update model with valid tokenization

Update to use fixed HF-compat selfies tokenizer

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Upload repo

initial commit