noneabove1182@sh.itjust.worksMEnglish · 1 year agoBeginner questions threadplus-squarepinmessage-squaremessage-square24fedilinkarrow-up127arrow-down11
arrow-up126arrow-down1message-squareBeginner questions threadplus-squarepinnoneabove1182@sh.itjust.worksMEnglish · 1 year agomessage-square24fedilink
Blaed@lemmy.worldEnglish · 1 year agoFree Open-Source AI LLM Guideplus-squarepinmessage-squaremessage-square4fedilinkarrow-up175arrow-down13
arrow-up172arrow-down1message-squareFree Open-Source AI LLM Guideplus-squarepinBlaed@lemmy.worldEnglish · 1 year agomessage-square4fedilink
Smorty [she/her]@lemmy.blahaj.zoneEnglish · 3 hours agoHaving trouble to generate correct output? Try prefixes!plus-squaremessage-squaremessage-square3fedilinkarrow-up17arrow-down10
arrow-up17arrow-down1message-squareHaving trouble to generate correct output? Try prefixes!plus-squareSmorty [she/her]@lemmy.blahaj.zoneEnglish · 3 hours agomessage-square3fedilink
EffortlessOps@sh.itjust.worksEnglish · 1 month agoMeta unveils open-source Llama Stack, standardizing AI building blocks across the entire development lifecycle.plus-squaregithub.comexternal-linkmessage-square0fedilinkarrow-up125arrow-down10
arrow-up125arrow-down1external-linkMeta unveils open-source Llama Stack, standardizing AI building blocks across the entire development lifecycle.plus-squaregithub.comEffortlessOps@sh.itjust.worksEnglish · 1 month agomessage-square0fedilink
brucethemoose@lemmy.worldEnglish · edit-22 months agoQwen2.5: A Party of Foundation Models!plus-squareqwenlm.github.ioexternal-linkmessage-square0fedilinkarrow-up114arrow-down10
arrow-up114arrow-down1external-linkQwen2.5: A Party of Foundation Models!plus-squareqwenlm.github.iobrucethemoose@lemmy.worldEnglish · edit-22 months agomessage-square0fedilink
Smokeydope@lemmy.worldEnglish · 2 months agoTesting the Limits: My GTX 1070 Rig vs Mistral Small 22Bplus-squaremessage-squaremessage-square13fedilinkarrow-up135arrow-down10
arrow-up135arrow-down1message-squareTesting the Limits: My GTX 1070 Rig vs Mistral Small 22Bplus-squareSmokeydope@lemmy.worldEnglish · 2 months agomessage-square13fedilink
hendrik@palaver.p3x.deEnglish · edit-212 days agoIs Arli AI a legit cloud LLM inference service? Any user experience?plus-squaremessage-squaremessage-square4fedilinkarrow-up16arrow-down11
arrow-up15arrow-down1message-squareIs Arli AI a legit cloud LLM inference service? Any user experience?plus-squarehendrik@palaver.p3x.deEnglish · edit-212 days agomessage-square4fedilink
Lumberjacked@lemmy.worldEnglish · 3 months agoLocal Notetaker for meetingsplus-squaremessage-squaremessage-square1fedilinkarrow-up112arrow-down10
arrow-up112arrow-down1message-squareLocal Notetaker for meetingsplus-squareLumberjacked@lemmy.worldEnglish · 3 months agomessage-square1fedilink
fran@lemmy.dbzer0.comEnglish · 3 months agoAre there any good open source text-to-music models, preferably with lyrical abilities?plus-squaremessage-squaremessage-square4fedilinkarrow-up120arrow-down13
arrow-up117arrow-down1message-squareAre there any good open source text-to-music models, preferably with lyrical abilities?plus-squarefran@lemmy.dbzer0.comEnglish · 3 months agomessage-square4fedilink
Bazsalanszky@lemmy.toldi.euEnglish · 3 months agoMistral AI just dropped their new model, Mistral Large 2plus-squaremistral.aiexternal-linkmessage-square4fedilinkarrow-up139arrow-down11
arrow-up138arrow-down1external-linkMistral AI just dropped their new model, Mistral Large 2plus-squaremistral.aiBazsalanszky@lemmy.toldi.euEnglish · 3 months agomessage-square4fedilink
Bazsalanszky@lemmy.toldi.euEnglish · 3 months agoLlama 3.1 is out!plus-squareai.meta.comexternal-linkmessage-square11fedilinkarrow-up149arrow-down14
arrow-up145arrow-down1external-linkLlama 3.1 is out!plus-squareai.meta.comBazsalanszky@lemmy.toldi.euEnglish · 3 months agomessage-square11fedilink
yokonzo@lemmy.worldEnglish · edit-24 months agoTrying to set up LLama but i get a error saying CUDA has no path setplus-squaremessage-squaremessage-square10fedilinkarrow-up17arrow-down11
arrow-up16arrow-down1message-squareTrying to set up LLama but i get a error saying CUDA has no path setplus-squareyokonzo@lemmy.worldEnglish · edit-24 months agomessage-square10fedilink
Martin@discuss.tchncs.deEnglish · 4 months agoA font with an LLM embeddedplus-squarefuglede.github.ioexternal-linkmessage-square4fedilinkarrow-up133arrow-down11
arrow-up132arrow-down1external-linkA font with an LLM embeddedplus-squarefuglede.github.ioMartin@discuss.tchncs.deEnglish · 4 months agomessage-square4fedilink
General_Effort@lemmy.worldEnglish · 5 months agoSharing new research, models, and datasets from Meta FAIRplus-squareai.meta.comexternal-linkmessage-square0fedilinkarrow-up18arrow-down11
arrow-up17arrow-down1external-linkSharing new research, models, and datasets from Meta FAIRplus-squareai.meta.comGeneral_Effort@lemmy.worldEnglish · 5 months agomessage-square0fedilink
General_Effort@lemmy.worldEnglish · 5 months agoPublishers Target Common Crawl In Fight Over AI Training Dataplus-squarewww.wired.comexternal-linkmessage-square0fedilinkarrow-up15arrow-down10
arrow-up15arrow-down1external-linkPublishers Target Common Crawl In Fight Over AI Training Dataplus-squarewww.wired.comGeneral_Effort@lemmy.worldEnglish · 5 months agomessage-square0fedilink
paintenzeroEnglish · 5 months ago[Question] Why is there no Q8 quantization for Phi-3-V?plus-squaremessage-squaremessage-square1fedilinkarrow-up18arrow-down10
arrow-up18arrow-down1message-square[Question] Why is there no Q8 quantization for Phi-3-V?plus-squarepaintenzeroEnglish · 5 months agomessage-square1fedilink
rufus@discuss.tchncs.deEnglish · edit-25 months ago[Paper] Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in SOTA Large Language Modelsplus-squarearxiv.orgexternal-linkmessage-square4fedilinkarrow-up124arrow-down10
arrow-up124arrow-down1external-link[Paper] Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in SOTA Large Language Modelsplus-squarearxiv.orgrufus@discuss.tchncs.deEnglish · edit-25 months agomessage-square4fedilink
Possibly linux@lemmy.zipEnglish · 5 months agoDoes anyone know where the old original GPT-2 (transformer) model ended up?plus-squaremessage-squaremessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareDoes anyone know where the old original GPT-2 (transformer) model ended up?plus-squarePossibly linux@lemmy.zipEnglish · 5 months agomessage-square0fedilink
Possibly linux@lemmy.zipEnglish · 5 months agoDoes anyone know where the old original GPT-2 (transformer) model ended up?plus-squaremessage-squaremessage-square2fedilinkarrow-up125arrow-down11
arrow-up124arrow-down1message-squareDoes anyone know where the old original GPT-2 (transformer) model ended up?plus-squarePossibly linux@lemmy.zipEnglish · 5 months agomessage-square2fedilink
OpticalMoose@discuss.tchncs.deEnglish · edit-25 months agoLooking for upgrade advice. Anyone building their supercomputer out of 3060s?plus-squaremessage-squaremessage-square8fedilinkarrow-up115arrow-down11
arrow-up114arrow-down1message-squareLooking for upgrade advice. Anyone building their supercomputer out of 3060s?plus-squareOpticalMoose@discuss.tchncs.deEnglish · edit-25 months agomessage-square8fedilink