Modelpublic

cybershiptrooper/grpo-continuous_weight_1.4-RM-n_examples_200-probe_layers_10

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes1downloads

file.gitattributes1 KBdownload

fileconfig.json759 Bdownload

filemodel-00001-of-00003.safetensors4.60 GBdownload

filemodel-00002-of-00003.safetensors4.61 GBdownload

filemodel-00003-of-00003.safetensors3.34 GBdownload

filemodel.safetensors.index.json23 KBdownload

filespecial_tokens_map.json437 Bdownload

filetokenizer_config.json1014 Bdownload

filetokenizer.json3.5 MBdownload

filetokenizer.model488 KBdownload

filetraining_args.bin6 KBdownload

cybershiptrooper/grpo-continuous_weight_1.4-RM-n_examples_200-probe_layers_10 · main · files are served by the source, never re-hosted here