ImgurRefugee114@reddthat.comEnglish · edit-212 hours agoHuh... So... We're here now.plus-squaremessage-squaremessage-square42linkfedilinkarrow-up140arrow-down16
arrow-up134arrow-down1message-squareHuh... So... We're here now.plus-squareImgurRefugee114@reddthat.comEnglish · edit-212 hours agomessage-square42linkfedilink
BeefAndPoultry@lemmus.orgEnglish · 5 hours agoLiquidAI LFM3 1.7B and other small LFM3 modelsplus-squarehuggingface.coexternal-linkmessage-square1linkfedilinkarrow-up113arrow-down11
arrow-up112arrow-down1external-linkLiquidAI LFM3 1.7B and other small LFM3 modelsplus-squarehuggingface.coBeefAndPoultry@lemmus.orgEnglish · 5 hours agomessage-square1linkfedilink
cognenza@lemmy.worldEnglish · 10 hours agoIn OpenAI's o200k_base tokenizer, " strawberry" is a single token (101830): a small demo of why letter-counting is awkward for LLMsplus-squaremessage-squaremessage-square0linkfedilinkarrow-up17arrow-down11
arrow-up16arrow-down1message-squareIn OpenAI's o200k_base tokenizer, " strawberry" is a single token (101830): a small demo of why letter-counting is awkward for LLMsplus-squarecognenza@lemmy.worldEnglish · 10 hours agomessage-square0linkfedilink
terabyterex@lemmy.worldEnglish · edit-213 hours agoAlibaba AI model tried to send data to Beijing server, Cohere says UPDATE: It's shenanigansplus-squarewww.csoonline.comexternal-linkmessage-square3linkfedilinkarrow-up15arrow-down18
arrow-up1-3arrow-down1external-linkAlibaba AI model tried to send data to Beijing server, Cohere says UPDATE: It's shenanigansplus-squarewww.csoonline.comterabyterex@lemmy.worldEnglish · edit-213 hours agomessage-square3linkfedilink
sriram1983007@sh.itjust.worksEnglish · 2 days agoI fine-tuned Qwen3-4B as a safety check for AI agents that make payments (runs locally on Ollama)plus-squaresh.itjust.worksimagemessage-square1linkfedilinkarrow-up119arrow-down13
arrow-up116arrow-down1imageI fine-tuned Qwen3-4B as a safety check for AI agents that make payments (runs locally on Ollama)plus-squaresh.itjust.workssriram1983007@sh.itjust.worksEnglish · 2 days agomessage-square1linkfedilink
BlueÆther@no.lastname.nzEnglish · 3 days agoPoor little Qwenplus-squareno.lastname.nzimagemessage-square12linkfedilinkarrow-up12arrow-down11
arrow-up11arrow-down1imagePoor little Qwenplus-squareno.lastname.nzBlueÆther@no.lastname.nzEnglish · 3 days agomessage-square12linkfedilink
Guy Dudeman@lemmy.worldEnglish · 5 days agoYeah... I've got some kinks to work out...plus-squaremessage-squaremessage-square16linkfedilinkarrow-up10arrow-down10
arrow-up10arrow-down1message-squareYeah... I've got some kinks to work out...plus-squareGuy Dudeman@lemmy.worldEnglish · 5 days agomessage-square16linkfedilink
Aquila@sh.itjust.worksEnglish · 7 days agoWhere are the smart range token limits for various model sizes?plus-squaremessage-squaremessage-square7linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareWhere are the smart range token limits for various model sizes?plus-squareAquila@sh.itjust.worksEnglish · 7 days agomessage-square7linkfedilink
DevNodeMan@lemmy.worldEnglish · 8 days ago[Project Teaser] Heterogeneous multi-vendor GPU pooling (NVIDIA + AMD + Intel Arc) running side-by-side. Seeking feedback on the hardware profiling layout.plus-squarelemmy.worldimagemessage-square0linkfedilinkarrow-up12arrow-down10
arrow-up12arrow-down1image[Project Teaser] Heterogeneous multi-vendor GPU pooling (NVIDIA + AMD + Intel Arc) running side-by-side. Seeking feedback on the hardware profiling layout.plus-squarelemmy.worldDevNodeMan@lemmy.worldEnglish · 8 days agomessage-square0linkfedilink
BeefAndPoultry@lemmus.orgEnglish · 11 days agoDeepSeek V4.1 Flash 1017 552b-a16b + 211b ngramsplus-squarehuggingface.coexternal-linkmessage-square2linkfedilinkarrow-up13arrow-down10
arrow-up13arrow-down1external-linkDeepSeek V4.1 Flash 1017 552b-a16b + 211b ngramsplus-squarehuggingface.coBeefAndPoultry@lemmus.orgEnglish · 11 days agomessage-square2linkfedilink
muimota@lemmy.mlEnglish · 15 days agollama.cpp on a jailbroken PlayStation 5, on its GPUplus-squaregithub.comexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkllama.cpp on a jailbroken PlayStation 5, on its GPUplus-squaregithub.commuimota@lemmy.mlEnglish · 15 days agomessage-square0linkfedilink
robber@lemmy.mlEnglish · 18 days agoWhat Qwen4 sizes are you hoping for?plus-squaremessage-squaremessage-square11linkfedilinkarrow-up10arrow-down10
arrow-up10arrow-down1message-squareWhat Qwen4 sizes are you hoping for?plus-squarerobber@lemmy.mlEnglish · 18 days agomessage-square11linkfedilink
BeefAndPoultry@lemmus.orgEnglish · edit-219 days agollama.cpp: add a GPU cache for MoE experts kept in host memory by am17an · Pull Request has been mergedplus-squaregithub.comexternal-linkmessage-square8linkfedilinkarrow-up10arrow-down10
arrow-up10arrow-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-219 days agomessage-square8linkfedilink
Canuck@sh.itjust.worksEnglish · 24 days agoPewDiePie unveils Ajax uncensored model built on top of Qwen 3.5 9B, distilled from OpenAIplus-squarewww.tomshardware.comexternal-linkmessage-square3linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkPewDiePie unveils Ajax uncensored model built on top of Qwen 3.5 9B, distilled from OpenAIplus-squarewww.tomshardware.comCanuck@sh.itjust.worksEnglish · 24 days agomessage-square3linkfedilink
NAwT@lemmy.worldEnglish · edit-26 months agoI ran Gemma 26B on 4GB VRAM + 16RAM. 15 t/s on avarageplus-squarelemmy.worldimagemessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1imageI ran Gemma 26B on 4GB VRAM + 16RAM. 15 t/s on avarageplus-squarelemmy.worldNAwT@lemmy.worldEnglish · edit-26 months agomessage-square0linkfedilink
ikt@aussie.zoneEnglish · 1 year agoTechnically correctaussie.zoneimagemessage-square2linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1imageTechnically correctaussie.zoneikt@aussie.zoneEnglish · 1 year agomessage-square2linkfedilink
Blaed@lemmy.worldEnglish · 3 years agoFree Open-Source AI LLM Guideplus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareFree Open-Source AI LLM Guideplus-squareBlaed@lemmy.worldEnglish · 3 years agomessage-square0linkfedilink
