artificialfish@programming.dev to LocalLLaMA@sh.itjust.worksEnglish · 10 hours agoHas anyone applied tree of thought prompting to r1 yet?message-squaremessage-square5fedilinkarrow-up19arrow-down11file-text
arrow-up18arrow-down1message-squareHas anyone applied tree of thought prompting to r1 yet?artificialfish@programming.dev to LocalLLaMA@sh.itjust.worksEnglish · 10 hours agomessage-square5fedilinkfile-text
minus-squareartificialfish@programming.devOPlinkfedilinkEnglisharrow-up1·3 hours agoWell I think you actually need to train a “discriminator” model on rationality tests. Probably an encoder only model like BERT just to assign a score to thoughts. Then you do monte carlo tree search.
Well I think you actually need to train a “discriminator” model on rationality tests. Probably an encoder only model like BERT just to assign a score to thoughts. Then you do monte carlo tree search.