Modelpublic

Holarissun/dpo_anthropic_hh_gamma3.0_beta0.1_subset20000_modelmistral7b-sft_maxsteps1250_bz32_lr1e-06

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes42downloads

root

file.gitattributes1 KBdownload

fileadapter_config.json652 Bdownload

fileadapter_model.safetensors52.0 MBdownload

fileREADME.md1 KBdownload

filespecial_tokens_map.json551 Bdownload

filetokenizer_config.json969 Bdownload

filetokenizer.json1.7 MBdownload

filetokenizer.model482 KBdownload

filetraining_args.bin5 KBdownload

Holarissun/dpo_anthropic_hh_gamma3.0_beta0.1_subset20000_modelmistral7b-sft_maxsteps1250_bz32_lr1e-06 · main · files are served by the source, never re-hosted here