noneabove1182@sh.itjust.worksMEnglish · 1 year agoBeginner questions threadplus-squarepinmessage-squaremessage-square0fedilinkarrow-up11
arrow-up11message-squareBeginner questions threadplus-squarepinnoneabove1182@sh.itjust.worksMEnglish · 1 year agomessage-square0fedilink
artificialfish@programming.devEnglish · 19 hours agoHas anyone applied tree of thought prompting to r1 yet?plus-squaremessage-squaremessage-square6fedilinkarrow-up110
arrow-up110message-squareHas anyone applied tree of thought prompting to r1 yet?plus-squareartificialfish@programming.devEnglish · 19 hours agomessage-square6fedilink
ikt@aussie.zoneEnglish · 21 hours agoMistral Small 3 (24B) releasedplus-squaremistral.aiexternal-linkmessage-square0fedilinkarrow-up115
arrow-up115external-linkMistral Small 3 (24B) releasedplus-squaremistral.aiikt@aussie.zoneEnglish · 21 hours agomessage-square0fedilink
ikt@aussie.zoneEnglish · 4 days agoDid DeepSeek R1 just pop nvidias bubble?plus-squarewww.youtube.comexternal-linkmessage-square8fedilinkarrow-up121
arrow-up121external-linkDid DeepSeek R1 just pop nvidias bubble?plus-squarewww.youtube.comikt@aussie.zoneEnglish · 4 days agomessage-square8fedilink
Smokeydope@lemmy.worldEnglish · edit-25 days agoWhy llms are suprisingly good at math, and what it means to process language.plus-squarelemmy.worldimagemessage-square19fedilinkarrow-up138
arrow-up138imageWhy llms are suprisingly good at math, and what it means to process language.plus-squarelemmy.worldSmokeydope@lemmy.worldEnglish · edit-25 days agomessage-square19fedilink
Smokeydope@lemmy.worldEnglish · edit-27 days agoThoughts on new deepseek R1 distill modelsplus-squaremessage-squaremessage-square7fedilinkarrow-up124
arrow-up124message-squareThoughts on new deepseek R1 distill modelsplus-squareSmokeydope@lemmy.worldEnglish · edit-27 days agomessage-square7fedilink
brokenlcd@feddit.itEnglish · 20 days agounsure on how to quantize modelplus-squaremessage-squaremessage-square5fedilinkarrow-up112
arrow-up112message-squareunsure on how to quantize modelplus-squarebrokenlcd@feddit.itEnglish · 20 days agomessage-square5fedilink
🇦🇺𝕄𝕦𝕟𝕥𝕖𝕕𝕔𝕣𝕠𝕔𝕕𝕚𝕝𝕖@lemm.eeEnglish · 21 days agoHow much gpu do i need to run a 90b modelplus-squaremessage-squaremessage-square16fedilinkarrow-up113
arrow-up113message-squareHow much gpu do i need to run a 90b modelplus-square🇦🇺𝕄𝕦𝕟𝕥𝕖𝕕𝕔𝕣𝕠𝕔𝕕𝕚𝕝𝕖@lemm.eeEnglish · 21 days agomessage-square16fedilink
Smokeydope@lemmy.worldEnglish · 22 days agoNvidia Digits AI Supercomputer just announcedplus-squarelemmy.worldimagemessage-square0fedilinkarrow-up19
arrow-up19imageNvidia Digits AI Supercomputer just announcedplus-squarelemmy.worldSmokeydope@lemmy.worldEnglish · 22 days agomessage-square0fedilink
Halo@lemmy.worldEnglish · 27 days agoGo toolchain error - Does anyone know what's going on here? lemmy.worldimagemessage-square10fedilinkarrow-up115
arrow-up115imageGo toolchain error - Does anyone know what's going on here? lemmy.worldHalo@lemmy.worldEnglish · 27 days agomessage-square10fedilink
hendrik@palaver.p3x.deEnglish · edit-21 month ago(New) papers by Meta: Large Concept Models and BLTplus-squaremessage-squaremessage-square2fedilinkarrow-up113
arrow-up113message-square(New) papers by Meta: Large Concept Models and BLTplus-squarehendrik@palaver.p3x.deEnglish · edit-21 month agomessage-square2fedilink
BB84@mander.xyzEnglish · edit-21 month agoNew open-weight 🐋 DeepSeek V3. 685B MoE. Beats Claude 3.5 Sonnet on Aider coding benchmarkplus-squarehuggingface.coexternal-linkmessage-square2fedilinkarrow-up16
arrow-up16external-linkNew open-weight 🐋 DeepSeek V3. 685B MoE. Beats Claude 3.5 Sonnet on Aider coding benchmarkplus-squarehuggingface.coBB84@mander.xyzEnglish · edit-21 month agomessage-square2fedilink
hok@lemmy.dbzer0.comEnglish · edit-21 month agoCan you fine-tune on localized steering of an LLM?plus-squaremessage-squaremessage-square0fedilinkarrow-up11
arrow-up11message-squareCan you fine-tune on localized steering of an LLM?plus-squarehok@lemmy.dbzer0.comEnglish · edit-21 month agomessage-square0fedilink
mapumbaa@lemmy.zipEnglish · 2 months agoQuestions about HW for local LLM.plus-squaremessage-squaremessage-square1fedilinkarrow-up12
arrow-up12message-squareQuestions about HW for local LLM.plus-squaremapumbaa@lemmy.zipEnglish · 2 months agomessage-square1fedilink
HumanPerson@sh.itjust.worksEnglish · edit-22 months agoFixed itplus-squaresh.itjust.worksimagemessage-square0fedilinkarrow-up12
arrow-up12imageFixed itplus-squaresh.itjust.worksHumanPerson@sh.itjust.worksEnglish · edit-22 months agomessage-square0fedilink
hok@lemmy.dbzer0.comEnglish · 2 months agoLlama 3.3 70b - End of open-weight pretrained models from Meta or just a better Llama 3.1 405b finetune?plus-squaremessage-squaremessage-square0fedilinkarrow-up11
arrow-up11message-squareLlama 3.3 70b - End of open-weight pretrained models from Meta or just a better Llama 3.1 405b finetune?plus-squarehok@lemmy.dbzer0.comEnglish · 2 months agomessage-square0fedilink
projectmoon@lemm.eeEnglish · edit-22 months agoOpenWebUI OpenStreetMap Tool 2.1.0plus-squareopenwebui.comexternal-linkmessage-square0fedilinkarrow-up11
arrow-up11external-linkOpenWebUI OpenStreetMap Tool 2.1.0plus-squareopenwebui.comprojectmoon@lemm.eeEnglish · edit-22 months agomessage-square0fedilink
lynx@sh.itjust.worksEnglish · 2 months agoQwen2.5-Coder-7Bplus-squaremessage-squaremessage-square0fedilinkarrow-up12
arrow-up12message-squareQwen2.5-Coder-7Bplus-squarelynx@sh.itjust.worksEnglish · 2 months agomessage-square0fedilink
Smorty [she/her]@lemmy.blahaj.zoneEnglish · 3 months agoHaving trouble to generate correct output? Try prefixes!plus-squaremessage-squaremessage-square0fedilinkarrow-up12
arrow-up12message-squareHaving trouble to generate correct output? Try prefixes!plus-squareSmorty [she/her]@lemmy.blahaj.zoneEnglish · 3 months agomessage-square0fedilink
EffortlessOps@sh.itjust.worksEnglish · 4 months agoMeta unveils open-source Llama Stack, standardizing AI building blocks across the entire development lifecycle.plus-squaregithub.comexternal-linkmessage-square0fedilinkarrow-up12
arrow-up12external-linkMeta unveils open-source Llama Stack, standardizing AI building blocks across the entire development lifecycle.plus-squaregithub.comEffortlessOps@sh.itjust.worksEnglish · 4 months agomessage-square0fedilink
