CoolFace
Modelpublic

W-61/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.05

sourceHugging Faceupdated 5mo agoView on Hugging Face
0likes16downloads
root
file.gitattributes2 KBdownload
fileall_results.json231 Bdownload
fileconfig.json688 Bdownload
filegeneration_config.json172 Bdownload
filemodel-00001-of-00007.safetensors4.55 GBdownload
filemodel-00002-of-00007.safetensors4.50 GBdownload
filemodel-00003-of-00007.safetensors4.66 GBdownload
filemodel-00004-of-00007.safetensors4.66 GBdownload
filemodel-00005-of-00007.safetensors4.50 GBdownload
filemodel-00006-of-00007.safetensors4.66 GBdownload
filemodel-00007-of-00007.safetensors2.39 GBdownload
filemodel.safetensors.index.json23 KBdownload
fileREADME.md2 KBdownload
filespecial_tokens_map.json449 Bdownload
filetokenizer_config.json50 KBdownload
filetokenizer.json16.4 MBdownload
filetrain_results.json231 Bdownload
filetrainer_state.json572 KBdownload

W-61/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.05 · main · files are served by the source, never re-hosted here