@simple to [email protected] • 2 years agoMicrosoft Releases 1.3 Bn Parameter Language Model, Outperforms LLaMaanalyticsindiamag.commessage-square1arrow-up19arrow-down11file-textcross-posted to: technology[email protected]
arrow-up18arrow-down1external-linkMicrosoft Releases 1.3 Bn Parameter Language Model, Outperforms LLaMaanalyticsindiamag.com@simple to [email protected] • 2 years agomessage-square1file-textcross-posted to: technology[email protected]
I wonder if higher quality datasets are the future rather than using tons of internet scraped texts. Either way, neat model!
minus-squareBehohippylink4•2 years agoBad article title. This is the “Textbooks are all you need” paper from a few days ago. It’s programming focused and I think Python only. For general purpose LLM use, LLaMA is still better.
Bad article title. This is the “Textbooks are all you need” paper from a few days ago. It’s programming focused and I think Python only. For general purpose LLM use, LLaMA is still better.