Hugging Face's logo

mashinaalive
/
zephyr-7b-dpo-qlora

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
zephyr-7b-dpo-qlora / runs
  • 1 contributor
 History: 150 commits
mashinaalive's picture
mashinaalive
End of training
8cd5ed5 verified