Modelpublic

hzy/qwen1.5b-math-base-3-to-5-grpo_std_on-mi300x-3000-drgrpo-len-with-entropy-loss-step-980

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes5downloads

root

file.gitattributes2 KBdownload

fileadded_tokens.json605 Bdownload

fileconfig.json880 Bdownload

filegeneration_config.json121 Bdownload

filemerges.txt1.6 MBdownload

filemodel.safetensors3.31 GBdownload

filespecial_tokens_map.json616 Bdownload

filetokenizer_config.json7 KBdownload

filetokenizer.json10.9 MBdownload

filevocab.json2.6 MBdownload

hzy/qwen1.5b-math-base-3-to-5-grpo_std_on-mi300x-3000-drgrpo-len-with-entropy-loss-step-980 · main · files are served by the source, never re-hosted here