OpenLMLab / MOSS-RLHF

MOSS-RLHF
Apache License 2.0
1.2k stars 91 forks source link

reward_model准确率 #15

Open mingrenbuke opened 11 months ago

mingrenbuke commented 11 months ago

想请教下开源的中英文reward_model的准确率大概是多少呢?

Ablustrund commented 11 months ago

您好,详见技术报告第十页,有中英文reward model在trainset 和 evalset上面的准确率