minus-squareIxinDow@alien.topBtoLocalLLaMA•Training LLMs to follow procedure for Math gives an accuracy of 98.5%linkfedilinkEnglisharrow-up1·1 year agoCan you try one of Yi-34B’s variants? linkfedilink
minus-squareIxinDow@alien.topBtoLocalLLaMA•Introducing Tess: Tess-M with 200K Context LengthlinkfedilinkEnglisharrow-up1·1 year agoHow many tokens in your substack example? Do you have examples of using model for fiction with length 16K-40K tokens? linkfedilink
IxinDow@alien.topB to LocalLLaMAEnglish · 1 year agoHe must be very enlightened in using LLMalien.topimagemessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1imageHe must be very enlightened in using LLMalien.topIxinDow@alien.topB to LocalLLaMAEnglish · 1 year agomessage-square0fedilink
Can you try one of Yi-34B’s variants?