noneabove1182M to LocalLLaMAEnglish · 1 year agoMicrosoft makes new 1.3B coding LLM that outperforms all models on MBPP except GPT-4, reaches third place on HumanEval above GPT-3.5, and shows emergent propertiesarxiv.orgexternal-linkmessage-square2fedilinkarrow-up132arrow-down11cross-posted to: [email protected][email protected]
arrow-up131arrow-down1external-linkMicrosoft makes new 1.3B coding LLM that outperforms all models on MBPP except GPT-4, reaches third place on HumanEval above GPT-3.5, and shows emergent propertiesarxiv.orgnoneabove1182M to LocalLLaMAEnglish · 1 year agomessage-square2fedilinkcross-posted to: [email protected][email protected]
minus-squarehendrik@lemmy.mllinkfedilinkEnglisharrow-up2·1 year agoInteresting. Did they publish the model or dataset?
minus-squarenoneabove1182OPMlinkfedilinkEnglisharrow-up2·1 year agoHaven’t seen it yet but hoping it does go up
