Modelpublic

saiteja33/gemma2-2b-hdpo-zh

sourceHugging Faceotherupdated 4mo agoView on Hugging Face

0likes8downloads

file.gitattributes2 KBdownload

fileall_results.json1 KBdownload

filechat_template.jinja613 Bdownload

fileconfig.json1 KBdownload

fileeval_results.json849 Bdownload

filegeneration_config.json187 Bdownload

filemodel-00001-of-00002.safetensors4.65 GBdownload

filemodel-00002-of-00002.safetensors229.5 MBdownload

filemodel.safetensors.index.json24 KBdownload

fileREADME.md2 KBdownload

filespecial_tokens_map.json644 Bdownload

filetokenizer_config.json45 KBdownload

filetokenizer.json32.8 MBdownload

filetokenizer.model4.0 MBdownload

filetrain_results.json204 Bdownload

filetrainer_log.jsonl2 KBdownload

filetrainer_state.json8 KBdownload

filetraining_args.bin8 KBdownload

filetraining_hdpo_dist_reg.png39 KBdownload

filetraining_loss.png31 KBdownload

filetraining_rewards_accuracies.png40 KBdownload

saiteja33/gemma2-2b-hdpo-zh · main · files are served by the source, never re-hosted here