lawrence@lemmy.world to ChatGPT@lemmy.world · edit-29 个月前I made a question to Llama 3.1 8B, but forgot to paste the context textlemmy.worldimagemessage-square12fedilinkarrow-up171arrow-down16file-text
arrow-up165arrow-down1imageI made a question to Llama 3.1 8B, but forgot to paste the context textlemmy.worldlawrence@lemmy.world to ChatGPT@lemmy.world · edit-29 个月前message-square12fedilinkfile-text
Notes: I hit two times the <ENTER> key after the question. Don’t know if that affected the answer. I don’t have any preloaded context.
minus-squarelawrence@lemmy.worldOPlinkfedilinkarrow-up6·edit-29 个月前I didn’t try this ‘instruct’ model version. Do you recommend it?
minus-squareBakedCatboy@lemmy.mllinkfedilinkEnglisharrow-up3·9 个月前The :8b and :latest tags actually point to :8b-instruct-q4_0 so I think we’re already good. You can check the tags page on ollama library and see the hashes for each tag to see which ones match.
minus-squarePennomi@lemmy.worldlinkfedilinkEnglisharrow-up2·9 个月前Always pick the instruct version if you aren’t an expert.
minus-squareALERTlinkfedilinkEnglisharrow-up1·9 个月前I am a total noob in LLM, so I picked the largest model of 8B instructs.
I didn’t try this ‘instruct’ model version. Do you recommend it?
The :8b and :latest tags actually point to :8b-instruct-q4_0 so I think we’re already good. You can check the tags page on ollama library and see the hashes for each tag to see which ones match.
Always pick the instruct version if you aren’t an expert.
I am a total noob in LLM, so I picked the largest model of 8B instructs.