Covid-Plannedemic_@alien.topB to LocalLLaMA@poweruser.forumEnglish · 10 months agoWhat's the simplest way to run speculative decoding?plus-squaremessage-squaremessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareWhat's the simplest way to run speculative decoding?plus-squareCovid-Plannedemic_@alien.topB to LocalLLaMA@poweruser.forumEnglish · 10 months agomessage-square0fedilink
Covid-Plannedemic_@alien.topB to LocalLLaMA@poweruser.forumEnglish · 10 months agoYi-23B-Llama: Distil version of Yi-34B-Llamaplus-squarehuggingface.coexternal-linkmessage-square17fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkYi-23B-Llama: Distil version of Yi-34B-Llamaplus-squarehuggingface.coCovid-Plannedemic_@alien.topB to LocalLLaMA@poweruser.forumEnglish · 10 months agomessage-square17fedilink
Covid-Plannedemic_@alien.topB to LocalLLaMA@poweruser.forumEnglish · 10 months agoTraining on the rephrased test set is all you need: 13B models can reach GPT-4 performance in benchmarks with no contamination detectable by traditional methodsplus-squarelmsys.orgexternal-linkmessage-square10fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkTraining on the rephrased test set is all you need: 13B models can reach GPT-4 performance in benchmarks with no contamination detectable by traditional methodsplus-squarelmsys.orgCovid-Plannedemic_@alien.topB to LocalLLaMA@poweruser.forumEnglish · 10 months agomessage-square10fedilink