minus-squaremetacritical@alien.topBtoLocalLLaMA•Yi-34B vs Yi-34B-200K on sequences <32K and <4KlinkfedilinkEnglisharrow-up1·1 year agoHow are such models finetuned ? Is finetuning are retraining similar ? linkfedilink
How are such models finetuned ? Is finetuning are retraining similar ?