dwikitheduck
/

gen-inst-2-lite-dpo

Model card Files Files and versions

gen-inst-2-lite-dpo / README.md

dwikitheduck's picture

Trained with Unsloth

026094b verified 6 months ago

|

history blame contribute delete

63 Bytes

metadata

license: apache-2.0
tags:
  - unsloth
  - trl
  - dpo