Modelpublic

Holarissun/dpo_harmlessharmless_human_subset20000_modelgpt2_maxsteps5000_bz8_lr1e-05

sourceHugging Facemitupdated 2y agoView on Hugging Face

0likes5downloads

file.gitattributes1 KBdownload

fileadapter_config.json586 Bdownload

fileadapter_model.safetensors4.5 MBdownload

filemerges.txt446 KBdownload

fileREADME.md1 KBdownload

filespecial_tokens_map.json131 Bdownload

filetokenizer_config.json476 Bdownload

filetokenizer.json2.0 MBdownload

filetraining_args.bin5 KBdownload

filevocab.json779 KBdownload

Holarissun/dpo_harmlessharmless_human_subset20000_modelgpt2_maxsteps5000_bz8_lr1e-05 · main · files are served by the source, never re-hosted here