khasky@lemmy.world · edit-22 months agoFreeToken claims 39.3 tok/s for Qwen3.6-35B on an 8GB RTX 4060 laptop GPUplus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareFreeToken claims 39.3 tok/s for Qwen3.6-35B on an 8GB RTX 4060 laptop GPUplus-squarekhasky@lemmy.world · edit-22 months agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 6 months agoA Formal Comparison Between Chain of Thought and Latent Thoughtplus-squarearxiv.orgexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkA Formal Comparison Between Chain of Thought and Latent Thoughtplus-squarearxiv.org☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 6 months agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 6 months agoQwen-Scope: Turning Sparse Features into Development Tools for Large Language Modelsplus-squareqianwen-res.oss-accelerate.aliyuncs.comexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkQwen-Scope: Turning Sparse Features into Development Tools for Large Language Modelsplus-squareqianwen-res.oss-accelerate.aliyuncs.com☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 6 months agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 6 months agoBuild yourself flowersplus-squarevickiboykis.comexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkBuild yourself flowersplus-squarevickiboykis.com☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 6 months agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 7 months agoLearning to Reason in 13 Parametersarxiv.orgexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkLearning to Reason in 13 Parametersarxiv.org☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 7 months agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 1 year agoAndrej Karpathy — “We’re summoning ghosts, not building animals”plus-squarewww.youtube.comexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkAndrej Karpathy — “We’re summoning ghosts, not building animals”plus-squarewww.youtube.com☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 1 year agomessage-square0linkfedilink
TheracAriane@thebrainbin.org · 1 year agoA dialogue on Machine Learning 🤓🤓🤓plus-squarecodeberg.orgexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkA dialogue on Machine Learning 🤓🤓🤓plus-squarecodeberg.orgTheracAriane@thebrainbin.org · 1 year agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 1 year agoBreathing Life Into Sketches Using Text-to-Video Priorsplus-squarelivesketch.github.ioexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkBreathing Life Into Sketches Using Text-to-Video Priorsplus-squarelivesketch.github.io☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 1 year agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 1 year agoJan v1: 4B open model for web search with 91% SimpleQA, slightly outperforms Perplexity Proplus-squarearxiv.orgexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkJan v1: 4B open model for web search with 91% SimpleQA, slightly outperforms Perplexity Proplus-squarearxiv.org☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 1 year agomessage-square0linkfedilink
Phil Nelson@lemmy.mlEnglish · 1 year agoOpenCV 4.12.0 Is Now Availableplus-squareopencv.orgexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkOpenCV 4.12.0 Is Now Availableplus-squareopencv.orgPhil Nelson@lemmy.mlEnglish · 1 year agomessage-square0linkfedilink
tastemyglaive@lemmy.mlEnglish · 1 year agoAffiliations of the ICML 2025 papersplus-squarelemmy.mlimagemessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1imageAffiliations of the ICML 2025 papersplus-squarelemmy.mltastemyglaive@lemmy.mlEnglish · 1 year agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 1 year agoThe Bitter Lesson is coming for Tokenizationplus-squarelucalp.devexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkThe Bitter Lesson is coming for Tokenizationplus-squarelucalp.dev☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 1 year agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 years agoThe Attention Mechanism Born for Cost Optimizationplus-squareoilbeater.comexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkThe Attention Mechanism Born for Cost Optimizationplus-squareoilbeater.com☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 years agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 years agoNeural Graffiti is an experiment in adding a "Spray Layer" to a transformer model, which injects a memory trace into the final stages of inference without finetuning or retrainingplus-squaregithub.comexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkNeural Graffiti is an experiment in adding a "Spray Layer" to a transformer model, which injects a memory trace into the final stages of inference without finetuning or retrainingplus-squaregithub.com☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 years agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 years agoWhy do LLMs make stuff up? New research peers under the hood.plus-squarearstechnica.comexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkWhy do LLMs make stuff up? New research peers under the hood.plus-squarearstechnica.com☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 years agomessage-square0linkfedilink
oba@lemmy.worldEnglish · 2 years agoMLOps tips I gathered recentlyplus-squarewww.readyforagents.comexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkMLOps tips I gathered recentlyplus-squarewww.readyforagents.comoba@lemmy.worldEnglish · 2 years agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 years agoDeepSeek open source DeepEP – library for MoE training and Inferencegithub.comexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkDeepSeek open source DeepEP – library for MoE training and Inferencegithub.com☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 years agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 years agoTowards Monosemanticity: Decomposing Language Models With Dictionary Learningplus-squaretransformer-circuits.pubexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkTowards Monosemanticity: Decomposing Language Models With Dictionary Learningplus-squaretransformer-circuits.pub☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 years agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 years agoScaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnetplus-squaretransformer-circuits.pubexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkScaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnetplus-squaretransformer-circuits.pub☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 years agomessage-square0linkfedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 years agoDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningarxiv.orgexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningarxiv.org☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 years agomessage-square0linkfedilink
