---
title: "Manyan samfuran harshe · Artificial systems · Halittu · Hasashen Kwaikwayo"
url: https://simulation-hypothesis.com/ha/entities/ai-llm
description: "Hanyoyin sadarwa na jijiyoyi na Transformer da aka horar don hasashen token na gaba a manyan tarin rubutu, sannan sau da yawa a gyara su da ra’ayin ɗan Adam."
license: https://creativecommons.org/licenses/by/4.0/
credit: "Ross Allan Dahl, Hasashen Kwaikwayo (simulation-hypothesis.com)"
---

[Halittu](https://simulation-hypothesis.com/ha/entities) › Tsarin wucin gadi

# Manyan samfuran harshe

Hanyoyin sadarwa na jijiyoyi na Transformer da aka horar don hasashen token na gaba a manyan tarin rubutu, sannan sau da yawa a gyara su da ra’ayin ɗan Adam.

Hanyoyin sadarwa na jijiyoyi na Transformer da aka horar don hasashen token na gaba a manyan tarin rubutu, sannan sau da yawa a gyara su da ra’ayin ɗan Adam. Suna amfani da self-attention a kan dukan taga mahallin. Takarda ɗaya ta 2020 ta ba da rahoton girman parameters biliyan 175\. Suna samar da harshe mai santsi, don haka fitarwa mai kama da ta ɗan Adam gwaji ne mara kyau na ƙwarewar ciki.

A cikin bishiyoyi

[Tsarin Transformer · Fasaha](https://simulation-hypothesis.com/ha/trees/technology?n=transformer)[Wakilai masu samarwa · Kwaikwayo](https://simulation-hypothesis.com/ha/trees/simulations?n=min-park)[Alamomin sanin AI · Ɗabi’a](https://simulation-hypothesis.com/ha/trees/ethics?n=c-butlin)[Ɗaukar jin daɗin AI da muhimmanci · Ɗabi’a](https://simulation-hypothesis.com/ha/trees/ethics?n=c-long)

## Tushe

* Vaswani A et al. (2017). Attention is all you need. NeurIPS. arXiv:1706.03762.
* Brown TB et al. (2020). Language models are few-shot learners. NeurIPS 33\. arXiv:2005.14165 (175B parameters).

Auna shi bisa ma’aunan da aka buga