NinjaMoves@feddit.nu to LocalLLaMAEnglish · 3 days agoMistral small 3.1 releasedmistral.aiexternal-linkmessage-square5fedilinkarrow-up126arrow-down11
arrow-up125arrow-down1external-linkMistral small 3.1 releasedmistral.aiNinjaMoves@feddit.nu to LocalLLaMAEnglish · 3 days agomessage-square5fedilink
minus-squarebrucethemoose@lemmy.worldlinkfedilinkEnglisharrow-up7·3 days agoAnyone tested it at high context yet? I find all Mistral models peter out after like 16K-24K tokes no matter what they advertise the context length as.
Anyone tested it at high context yet? I find all Mistral models peter out after like 16K-24K tokes no matter what they advertise the context length as.