Upload README.md

Preference alignment

Add plots for KTO training

Updated Readme.txt

Upload 18 files

Update the model weights

Update README.md

New version of the model trained with 4096 token context

Update README.md

Update README.md

Delete Psyfighter2-13B-vore_q4_k_m.gguf

Update README.md

Update README.md

Upload 16 files

initial commit