Modelpublic

yuhan-nlp/verl-grpo-medium-qwen3-4b-step100-repro

sourceHugging Facemitupdated 2mo agoView on Hugging Face

0likes78downloads

file.gitattributes2 KBdownload

fileadded_tokens.json707 Bdownload

filechat_template.jinja4 KBdownload

fileconfig.json2 KBdownload

filegeneration_config.json214 Bdownload

filemerges.txt1.6 MBdownload

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

filemodel-00002-of-00002.safetensors3.57 GBdownload

filemodel.safetensors.index.json32 KBdownload

fileREADME.md2 KBdownload

filespecial_tokens_map.json613 Bdownload

filetokenizer_config.json5 KBdownload

filetokenizer.json10.9 MBdownload

filevocab.json2.6 MBdownload

yuhan-nlp/verl-grpo-medium-qwen3-4b-step100-repro · main · files are served by the source, never re-hosted here