☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · edit-27 days agoBy using the same techniques Google used to solve Go (MTCS and backprop), Llama8B gets 96.7% on math benchmark GSM8K. That’s better than GPT-4, Claude and Gemini, with 200x fewer parameters!plus-squarearxiv.orgexternal-linkmessage-square2fedilinkarrow-up111arrow-down13
arrow-up18arrow-down1external-linkBy using the same techniques Google used to solve Go (MTCS and backprop), Llama8B gets 96.7% on math benchmark GSM8K. That’s better than GPT-4, Claude and Gemini, with 200x fewer parameters!plus-squarearxiv.org☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · edit-27 days agomessage-square2fedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 7 days agoMixture of Agents (MoA) leverages several open-source LLM agents to achieve a score of 65.1% on AlpacaEval 2.0plus-squarewww.together.aiexternal-linkmessage-square0fedilinkarrow-up17arrow-down11
arrow-up16arrow-down1external-linkMixture of Agents (MoA) leverages several open-source LLM agents to achieve a score of 65.1% on AlpacaEval 2.0plus-squarewww.together.ai☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 7 days agomessage-square0fedilink
ylai@lemmy.mlEnglish · 9 days agoFrom DeepSpeed to FSDP and Back Again with Hugging Face Accelerateplus-squarehuggingface.coexternal-linkmessage-square0fedilinkarrow-up14arrow-down10
arrow-up14arrow-down1external-linkFrom DeepSpeed to FSDP and Back Again with Hugging Face Accelerateplus-squarehuggingface.coylai@lemmy.mlEnglish · 9 days agomessage-square0fedilink
keepthepace@slrpnk.net · 13 days agoTorrent tracker for open modelsplus-squareaitracker.artexternal-linkmessage-square0fedilinkarrow-up19arrow-down11
arrow-up18arrow-down1external-linkTorrent tracker for open modelsplus-squareaitracker.artkeepthepace@slrpnk.net · 13 days agomessage-square0fedilink
wargreymon@sh.itjust.works · 13 days agoCan gpt generate a gpt model?plus-squaremessage-squaremessage-square5fedilinkarrow-up18arrow-down13
arrow-up15arrow-down1message-squareCan gpt generate a gpt model?plus-squarewargreymon@sh.itjust.works · 13 days agomessage-square5fedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 1 month agoSakuga-42M Dataset: Scaling Up Cartoon Researchplus-squarearxiv.orgexternal-linkmessage-square0fedilinkarrow-up13arrow-down12
arrow-up11arrow-down1external-linkSakuga-42M Dataset: Scaling Up Cartoon Researchplus-squarearxiv.org☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 1 month agomessage-square0fedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 1 month agoHow AI 'Understands' Images (CLIP)plus-squarewww.youtube.comexternal-linkmessage-square0fedilinkarrow-up16arrow-down11
arrow-up15arrow-down1external-linkHow AI 'Understands' Images (CLIP)plus-squarewww.youtube.com☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 1 month agomessage-square0fedilink
smokinliver@sopuli.xyz · edit-22 months agoWhere do these stains come from and how can I fix them?plus-squaresopuli.xyzimagemessage-square3fedilinkarrow-up110arrow-down11
arrow-up19arrow-down1imageWhere do these stains come from and how can I fix them?plus-squaresopuli.xyzsmokinliver@sopuli.xyz · edit-22 months agomessage-square3fedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 months agoHiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Modelsplus-squarehidiffusion.github.ioexternal-linkmessage-square0fedilinkarrow-up12arrow-down12
arrow-up10arrow-down1external-linkHiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Modelsplus-squarehidiffusion.github.io☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 months agomessage-square0fedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 months agoDynamic Typography: Bringing Text to Life via Video Diffusion Priorplus-squareanimate-your-word.github.ioexternal-linkmessage-square0fedilinkarrow-up14arrow-down11
arrow-up13arrow-down1external-linkDynamic Typography: Bringing Text to Life via Video Diffusion Priorplus-squareanimate-your-word.github.io☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 2 months agomessage-square0fedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 3 months agoNo "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performanceplus-squarearxiv.orgexternal-linkmessage-square0fedilinkarrow-up16arrow-down11
arrow-up15arrow-down1external-linkNo "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performanceplus-squarearxiv.org☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 3 months agomessage-square0fedilink
Kit@lemmy.blahaj.zone · 3 months agoWhat are your thoughts on Microsoft Copilot?plus-squaremessage-squaremessage-square15fedilinkarrow-up19arrow-down18
arrow-up11arrow-down1message-squareWhat are your thoughts on Microsoft Copilot?plus-squareKit@lemmy.blahaj.zone · 3 months agomessage-square15fedilink
The Hobbyist@lemmy.zip · 3 months agoLooking for a specific OpenAI employee personal blogplus-squaremessage-squaremessage-square3fedilinkarrow-up117arrow-down12
arrow-up115arrow-down1message-squareLooking for a specific OpenAI employee personal blogplus-squareThe Hobbyist@lemmy.zip · 3 months agomessage-square3fedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 3 months agoIntroducing SIMA, a Scalable Instructable Multiworld Agentplus-squaredeepmind.googleexternal-linkmessage-square0fedilinkarrow-up19arrow-down12
arrow-up17arrow-down1external-linkIntroducing SIMA, a Scalable Instructable Multiworld Agentplus-squaredeepmind.google☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 3 months agomessage-square0fedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 3 months agoLLMs are not superintelligent | Yann LeCun and Lex Fridmanplus-squarewww.youtube.comexternal-linkmessage-square0fedilinkarrow-up14arrow-down12
arrow-up12arrow-down1external-linkLLMs are not superintelligent | Yann LeCun and Lex Fridmanplus-squarewww.youtube.com☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 3 months agomessage-square0fedilink
ericjmorey@programming.dev · 4 months agoWhere Is Noether's Principle in Machine Learning? | 2024-02-29plus-squarecgad.skiexternal-linkmessage-square0fedilinkarrow-up14arrow-down10
arrow-up14arrow-down1external-linkWhere Is Noether's Principle in Machine Learning? | 2024-02-29plus-squarecgad.skiericjmorey@programming.dev · 4 months agomessage-square0fedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 4 months agoSora is an AI model that can create realistic and imaginative scenes from text instructions.openai.comexternal-linkmessage-square2fedilinkarrow-up14arrow-down12
arrow-up12arrow-down1external-linkSora is an AI model that can create realistic and imaginative scenes from text instructions.openai.com☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 4 months agomessage-square2fedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 4 months agoMastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMsplus-squaregithub.comexternal-linkmessage-square0fedilinkarrow-up12arrow-down11
arrow-up11arrow-down1external-linkMastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMsplus-squaregithub.com☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 4 months agomessage-square0fedilink
mawss@sh.itjust.works · 4 months agoGemini 1.5plus-squareblog.googleexternal-linkmessage-square0fedilinkarrow-up13arrow-down11
arrow-up12arrow-down1external-linkGemini 1.5plus-squareblog.googlemawss@sh.itjust.works · 4 months agomessage-square0fedilink
☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 4 months agoDiffusionGPT: LLM-Driven Text-to-Image Generation Systemplus-squarediffusiongpt.github.ioexternal-linkmessage-square0fedilinkarrow-up14arrow-down12
arrow-up12arrow-down1external-linkDiffusionGPT: LLM-Driven Text-to-Image Generation Systemplus-squarediffusiongpt.github.io☆ Yσɠƚԋσʂ ☆@lemmy.mlEnglish · 4 months agomessage-square0fedilink
