rglullis@communick.newsEnglish · 3 months agoLlama 4 is Hereplus-squarewww.llama.comexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkLlama 4 is Hereplus-squarewww.llama.comrglullis@communick.newsEnglish · 3 months agomessage-square0linkfedilink
rglullis@communick.newsEnglish · 5 months agoOpenAI's nightmare: Deepseek R1 on a Raspberry Piplus-squarewww.youtube.comexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkOpenAI's nightmare: Deepseek R1 on a Raspberry Piplus-squarewww.youtube.comrglullis@communick.newsEnglish · 5 months agomessage-square0linkfedilink
rglullis@communick.newsEnglish · 10 months agoBuild a Fully Local RAG App With PostgreSQL, Mistral, and Ollamawww.timescale.comexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkBuild a Fully Local RAG App With PostgreSQL, Mistral, and Ollamawww.timescale.comrglullis@communick.newsEnglish · 10 months agomessage-square0linkfedilink
sandys1@alien.topBEnglish · 2 years agowhich is the best model (finetuned or base) to extract structured data from a bunch of text?plus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squarewhich is the best model (finetuned or base) to extract structured data from a bunch of text?plus-squaresandys1@alien.topBEnglish · 2 years agomessage-square0linkfedilink
kadhi_chawal2@alien.topBEnglish · 2 years agoHow to start red teaming on llms ?plus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareHow to start red teaming on llms ?plus-squarekadhi_chawal2@alien.topBEnglish · 2 years agomessage-square0linkfedilink
ForsookComparison@alien.topBEnglish · 2 years agoCheapest GPU/Way to run 30b or 34b "Code" Models with GPT4ALL?plus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareCheapest GPU/Way to run 30b or 34b "Code" Models with GPT4ALL?plus-squareForsookComparison@alien.topBEnglish · 2 years agomessage-square0linkfedilink
currytrash97@alien.topBEnglish · 2 years agoA100 inference is much slower than expected with small batch sizeplus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareA100 inference is much slower than expected with small batch sizeplus-squarecurrytrash97@alien.topBEnglish · 2 years agomessage-square0linkfedilink
oobabooga4@alien.topBEnglish · 2 years agoQuIP#: SOTA 2-bit quantization method, now implemented in text-generation-webui (experimental)plus-squaregithub.comexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkQuIP#: SOTA 2-bit quantization method, now implemented in text-generation-webui (experimental)plus-squaregithub.comoobabooga4@alien.topBEnglish · 2 years agomessage-square0linkfedilink
PuzzledWhereas991@alien.topBEnglish · 2 years agoIs m1 max macbook pro worth?plus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareIs m1 max macbook pro worth?plus-squarePuzzledWhereas991@alien.topBEnglish · 2 years agomessage-square0linkfedilink
fluffywuffie90210@alien.topBEnglish · 2 years agoAnyone running 3 gpus? Looking for advice on best x670 that might be able to slot a third card on.plus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareAnyone running 3 gpus? Looking for advice on best x670 that might be able to slot a third card on.plus-squarefluffywuffie90210@alien.topBEnglish · 2 years agomessage-square0linkfedilink
Clark9292@alien.topBEnglish · 2 years agoPolitically balanced chat model?plus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squarePolitically balanced chat model?plus-squareClark9292@alien.topBEnglish · 2 years agomessage-square0linkfedilink
fakezeta@alien.topBEnglish · 2 years agoOptimum Intel OpenVino Performanceplus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareOptimum Intel OpenVino Performanceplus-squarefakezeta@alien.topBEnglish · 2 years agomessage-square0linkfedilink
qualaric@alien.topBEnglish · 2 years ago13b models chartplus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-square13b models chartplus-squarequalaric@alien.topBEnglish · 2 years agomessage-square0linkfedilink
shmishmouyes@alien.topBEnglish · 2 years agoMeta AI Researcher: "Big breakthrough last night. Really excited to share what we've been building with you guys soon."plus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareMeta AI Researcher: "Big breakthrough last night. Really excited to share what we've been building with you guys soon."plus-squareshmishmouyes@alien.topBEnglish · 2 years agomessage-square0linkfedilink
multiverse_fan@alien.topBEnglish · 2 years agoRunning Multiple WebUI instances (follow up from my question yesterday)plus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareRunning Multiple WebUI instances (follow up from my question yesterday)plus-squaremultiverse_fan@alien.topBEnglish · 2 years agomessage-square0linkfedilink
nightkall@alien.topBEnglish · 2 years agoLLM Visualization: 3D interactive model of a GPT-style LLM network running inference.plus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareLLM Visualization: 3D interactive model of a GPT-style LLM network running inference.plus-squarenightkall@alien.topBEnglish · 2 years agomessage-square0linkfedilink
DominicanGreg@alien.topBEnglish · 2 years agoHow to upgrade to the next VRAM breakpoints, and is it worth it?plus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareHow to upgrade to the next VRAM breakpoints, and is it worth it?plus-squareDominicanGreg@alien.topBEnglish · 2 years agomessage-square0linkfedilink
Heliogabulus@alien.topBEnglish · 2 years agoWhich local models are best for writing “literature”plus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareWhich local models are best for writing “literature”plus-squareHeliogabulus@alien.topBEnglish · 2 years agomessage-square0linkfedilink
lemon07r@alien.topBEnglish · 2 years agoDPO models seem to be pretty goodplus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareDPO models seem to be pretty goodplus-squarelemon07r@alien.topBEnglish · 2 years agomessage-square0linkfedilink
easyllaama@alien.topBEnglish · 2 years agoSo far GGUF is the best format as I realize it. Will NVlinked 2x3090 act like one 48GB?plus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareSo far GGUF is the best format as I realize it. Will NVlinked 2x3090 act like one 48GB?plus-squareeasyllaama@alien.topBEnglish · 2 years agomessage-square0linkfedilink
