Badr Youbi Idrissi
@byoubii
๊ฐ์
August 2015
133 ํ๋ก์ ์ค 308 ํฌ
What happens if we make language models predict several tokens ahead instead of only the next one? In this paper, we show that multi-token prediction boosts language model training efficiency. ๐งต 1/11
Paper:
Joint work with @FabianGloeckle
๋ ๋ณด๊ธฐ
