Modelpublic

a-F1/math-qwen2.5-3b-reinforce-moa-3x1-unshared-actor_lr7.5e-7-epoch2-modenull-cftrue-decayepsfalse

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes1downloads

root

direval_results/

dirgenerator_1/

dirgenerator_2/

file.gitattributes2 KBdownload

fileconfig.json708 Bdownload

filegeneration_config.json117 Bdownload

filemodel-00001-of-00002.safetensors4.62 GBdownload

filemodel-00002-of-00002.safetensors1.13 GBdownload

filemodel.safetensors.index.json35 KBdownload

a-F1/math-qwen2.5-3b-reinforce-moa-3x1-unshared-actor_lr7.5e-7-epoch2-modenull-cftrue-decayepsfalse · main · files are served by the source, never re-hosted here