Holarissun/dpo_harmlessharmless_gpt3_gamma0.0_beta0.1_subset20000_modelmistral7b_maxsteps5000_bz8_lr5e-06
07
This repository belongs to Holarissun on Hugging Face.
CoolFace never edits a repository it does not host. Visibility, licence, collaborators and gating are all managed at the source.
dpo_harmlessharmless_gpt3_gamma0.0_beta0.1_subset20000_modelmistral7b_maxsteps5000_bz8_lr5e-06
public
apache-2.0
no
Holarissun
