irradiated@radiation.partyMB to TechNews@radiation.party · 1 year ago[HN] Reinforced Self-Training (ReST) for Language Modelingarxiv.orgexternal-linkmessage-square0fedilinkarrow-up11arrow-down10file-textcross-posted to: [email protected]
arrow-up11arrow-down1external-link[HN] Reinforced Self-Training (ReST) for Language Modelingarxiv.orgirradiated@radiation.partyMB to TechNews@radiation.party · 1 year agomessage-square0fedilinkfile-textcross-posted to: [email protected]