a_beautiful_rhindB to LocalLLaMA@poweruser.forumEnglish · 10 months agoYet another 120b. Trained on limarp.huggingface.coexternal-linkmessage-square1fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkYet another 120b. Trained on limarp.huggingface.coa_beautiful_rhindB to LocalLLaMA@poweruser.forumEnglish · 10 months agomessage-square1fedilink
minus-squarettkciarBlinkfedilinkEnglisharrow-up1·10 months agoThis is a fine-tune of Goliath-120B. Didn’t the author hypothesize that Goliath’s interleaving of rows would degrade inference quality until it had been fine-tuned? It will be interesting to see if this fine-tune supports that hypothesis. Waiting for GUFF.
This is a fine-tune of Goliath-120B.
Didn’t the author hypothesize that Goliath’s interleaving of rows would degrade inference quality until it had been fine-tuned?
It will be interesting to see if this fine-tune supports that hypothesis.
Waiting for GUFF.