Hugging Face's logo

winglian
/
zephyr-deita-kto-3ep-v3-r256-bsz16

PEFT
TensorBoard
Safetensors
mistral
trl
dpo
Generated from Trainer
Model card Files
xet
Metrics Community
zephyr-deita-kto-3ep-v3-r256-bsz16 / runs
  • 1 contributor
 History: 1 commit
winglian's picture
winglian
End of training
adf288b verified