CoolFace
Modelpublic

Holarissun/REPROD_dpo_harmlessharmless_human_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06

sourceHugging Facegemmaupdated 2y agoView on Hugging Face
0likes6downloads
fileadapter_model.safetensors49.0 MBdownload
filetraining_args.bin5 KBdownload

Holarissun/REPROD_dpo_harmlessharmless_human_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06 · main · files are served by the source, never re-hosted here