Microsoft Releases 1.3 Bn Parameter Language Model, Outperforms LLaMa
Microsoft Releases 1.3 Bn Parameter Language Model, Outperforms LLaMa
analyticsindiamag.com Microsoft Releases 1.3 Bn Parameter Language Model, Outperforms LLaMa
Microsoft Research has upped the game with an even smaller model. phi-1 is a transformer based model with just 1.3 billion parameters.
cross-posted from: https://lemmy.world/post/422633
I wonder if high quality datasets is the future as opposed to using internet scraped data that might produce lower quality output. Either way, neat model!
0 comments