BeefAndPoultry@lemmus.orgEnglish · edit-223 hours agollama.cpp: add a GPU cache for MoE experts kept in host memory by am17an · Pull Request has been mergedplus-squaregithub.comexternal-linkmessage-square3linkfedilinkarrow-up123arrow-down11
arrow-up122arrow-down1external-linkllama.cpp: add a GPU cache for MoE experts kept in host memory by am17an · Pull Request has been mergedplus-squaregithub.comBeefAndPoultry@lemmus.orgEnglish · edit-223 hours agomessage-square3linkfedilink
ikt@aussie.zoneEnglish · edit-22 days ago🇪🇺 Mistral Large 4 Released!plus-squaremistral.aiexternal-linkmessage-square7linkfedilinkarrow-up127arrow-down15
arrow-up122arrow-down1external-link🇪🇺 Mistral Large 4 Released!plus-squaremistral.aiikt@aussie.zoneEnglish · edit-22 days agomessage-square7linkfedilink
MalReynolds@slrpnk.netEnglish · 5 days agoGood places to keep up to date on LLMs?plus-squaremessage-squaremessage-square35linkfedilinkarrow-up161arrow-down110
arrow-up151arrow-down1message-squareGood places to keep up to date on LLMs?plus-squareMalReynolds@slrpnk.netEnglish · 5 days agomessage-square35linkfedilink
BeefAndPoultry@lemmus.orgEnglish · 3 days agollama.cpp v0.6.0 released with support for GLM-5.3-Flash, MTP for Qwen4Exp, and moreplus-squaregithub.comexternal-linkmessage-square3linkfedilinkarrow-up132arrow-down10
arrow-up132arrow-down1external-linkllama.cpp v0.6.0 released with support for GLM-5.3-Flash, MTP for Qwen4Exp, and moreplus-squaregithub.comBeefAndPoultry@lemmus.orgEnglish · 3 days agomessage-square3linkfedilink
leanleft@lemmy.mlEnglish · edit-22 days agorequesting suggestions for models for comparison benchmarkplus-squaremessage-squaremessage-square1linkfedilinkarrow-up16arrow-down12
arrow-up14arrow-down1message-squarerequesting suggestions for models for comparison benchmarkplus-squareleanleft@lemmy.mlEnglish · edit-22 days agomessage-square1linkfedilink
leanleft@lemmy.mlEnglish · edit-215 hours agoJEV collection(zero-shot decision model) SHARE list of links HFplus-squaremessage-squaremessage-square9linkfedilinkarrow-up119arrow-down12
arrow-up117arrow-down1message-squareJEV collection(zero-shot decision model) SHARE list of links HFplus-squareleanleft@lemmy.mlEnglish · edit-215 hours agomessage-square9linkfedilink
Canuck@sh.itjust.worksEnglish · 5 days agoPewDiePie unveils Ajax uncensored model built on top of Qwen 3.5 9B, distilled from OpenAIplus-squarewww.tomshardware.comexternal-linkmessage-square6linkfedilinkarrow-up120arrow-down117
arrow-up13arrow-down1external-linkPewDiePie unveils Ajax uncensored model built on top of Qwen 3.5 9B, distilled from OpenAIplus-squarewww.tomshardware.comCanuck@sh.itjust.worksEnglish · 5 days agomessage-square6linkfedilink
Ropianos@feddit.orgEnglish · 7 days agoPi 1.0 releasedplus-squareearendil.comexternal-linkmessage-square3linkfedilinkarrow-up124arrow-down11
arrow-up123arrow-down1external-linkPi 1.0 releasedplus-squareearendil.comRopianos@feddit.orgEnglish · 7 days agomessage-square3linkfedilink
♠️ Critical Nexus ✊🏿@reddthat.comEnglish · 8 days agoOllama's new "Nimble" model is a 9B decision engine, not a chatbot — and it's fastplus-squaremessage-squaremessage-square9linkfedilinkarrow-up118arrow-down14
arrow-up114arrow-down1message-squareOllama's new "Nimble" model is a 9B decision engine, not a chatbot — and it's fastplus-square♠️ Critical Nexus ✊🏿@reddthat.comEnglish · 8 days agomessage-square9linkfedilink
Shatur@discuss.tchncs.deEnglish · 11 days ago42x Faster Prompt Lookup Drafting in llama.cppplus-squarejadidbourbaki.github.ioexternal-linkmessage-square1linkfedilinkarrow-up128arrow-down11
arrow-up127arrow-down1external-link42x Faster Prompt Lookup Drafting in llama.cppplus-squarejadidbourbaki.github.ioShatur@discuss.tchncs.deEnglish · 11 days agomessage-square1linkfedilink
Mystic Mushroom [Ze/Zir]@lemmy.dbzer0.comEnglish · 13 days agoPirate Face - a Pirate Bay for LLMsplus-squarepirateface.coexternal-linkmessage-square16linkfedilinkarrow-up171arrow-down16
arrow-up165arrow-down1external-linkPirate Face - a Pirate Bay for LLMsplus-squarepirateface.coMystic Mushroom [Ze/Zir]@lemmy.dbzer0.comEnglish · 13 days agomessage-square16linkfedilink
pepperfree@sh.itjust.worksEnglish · 14 days agoQwen3.8 27B prefiller from ISTA-DASLabplus-squarehuggingface.coexternal-linkmessage-square9linkfedilinkarrow-up119arrow-down11
arrow-up118arrow-down1external-linkQwen3.8 27B prefiller from ISTA-DASLabplus-squarehuggingface.copepperfree@sh.itjust.worksEnglish · 14 days agomessage-square9linkfedilink
leanleft@lemmy.mlEnglish · 14 days agonew model: [medical] FreedomIntelligence/HuatuoGPT-3-27Bplus-squarehuggingface.coexternal-linkmessage-square2linkfedilinkarrow-up18arrow-down11
arrow-up17arrow-down1external-linknew model: [medical] FreedomIntelligence/HuatuoGPT-3-27Bplus-squarehuggingface.coleanleft@lemmy.mlEnglish · 14 days agomessage-square2linkfedilink
BeefAndPoultry@lemmus.orgEnglish · 14 days agollama.cpp v0.5.0plus-squaregithub.comexternal-linkmessage-square0linkfedilinkarrow-up133arrow-down11
arrow-up132arrow-down1external-linkllama.cpp v0.5.0plus-squaregithub.comBeefAndPoultry@lemmus.orgEnglish · 14 days agomessage-square0linkfedilink
ikt@aussie.zoneEnglish · 16 days agoJev in 25 Lines of Pythonplus-squarewww.nobodywho.aiexternal-linkmessage-square2linkfedilinkarrow-up116arrow-down12
arrow-up114arrow-down1external-linkJev in 25 Lines of Pythonplus-squarewww.nobodywho.aiikt@aussie.zoneEnglish · 16 days agomessage-square2linkfedilink
Shatur@discuss.tchncs.deEnglish · 16 days agoQwen4-27B just confirmed discuss.tchncs.deimagemessage-square6linkfedilinkarrow-up143arrow-down15
arrow-up138arrow-down1imageQwen4-27B just confirmed discuss.tchncs.deShatur@discuss.tchncs.deEnglish · 16 days agomessage-square6linkfedilink
leanleft@lemmy.mlEnglish · edit-216 days agoCode2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolutionplus-squaremessage-squaremessage-square3linkfedilinkarrow-up16arrow-down11
arrow-up15arrow-down1message-squareCode2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolutionplus-squareleanleft@lemmy.mlEnglish · edit-216 days agomessage-square3linkfedilink
leanleft@lemmy.mlEnglish · 17 days agoToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruningplus-squaremessage-squaremessage-square12linkfedilinkarrow-up115arrow-down12
arrow-up113arrow-down1message-squareToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruningplus-squareleanleft@lemmy.mlEnglish · 17 days agomessage-square12linkfedilink
leanleft@lemmy.mlEnglish · edit-218 days agoold model: Qwen3.6-35B-A3B-BUDGET-GGUFplus-squarehuggingface.coexternal-linkmessage-square1linkfedilinkarrow-up110arrow-down12
arrow-up18arrow-down1external-linkold model: Qwen3.6-35B-A3B-BUDGET-GGUFplus-squarehuggingface.coleanleft@lemmy.mlEnglish · edit-218 days agomessage-square1linkfedilink
Luccus@feddit.orgEnglish · edit-218 days agoWhat's the motivation behind vibe-hobbying?plus-squaremessage-squaremessage-square50linkfedilinkarrow-up138arrow-down14
arrow-up134arrow-down1message-squareWhat's the motivation behind vibe-hobbying?plus-squareLuccus@feddit.orgEnglish · edit-218 days agomessage-square50linkfedilink
