Byte Latent Transformer: Patches Scale Better Than Tokens
Новая статья от META - Byte Latent Transformer. Пробуют новый подход к токенизации - вместо фиксированного словаря используют динамические patches, размер которых определяется по энтропии следующего байта. Модель успешно масштабировали до 8B параметров и 4T байтов, при этом с лучшим качеством. Плюс эффективность и тренировки, и инференса лучше. Каких-то особых недостатков подхода авторы не описали. Ждём Llama 4 на байтах? :)
Byte Latent Transformer: Patches Scale Better Than Tokens
Новая статья от META - Byte Latent Transformer. Пробуют новый подход к токенизации - вместо фиксированного словаря используют динамические patches, размер которых определяется по энтропии следующего байта. Модель успешно масштабировали до 8B параметров и 4T байтов, при этом с лучшим качеством. Плюс эффективность и тренировки, и инференса лучше. Каких-то особых недостатков подхода авторы не описали. Ждём Llama 4 на байтах? :)
Stocks closed in the red Friday as investors weighed upbeat remarks from Russian President Vladimir Putin about diplomatic discussions with Ukraine against a weaker-than-expected print on U.S. consumer sentiment. Friday’s performance was part of a larger shift. For the week, the Dow, S&P 500 and Nasdaq fell 2%, 2.9%, and 3.5%, respectively. At its heart, Telegram is little more than a messaging app like WhatsApp or Signal. But it also offers open channels that enable a single user, or a group of users, to communicate with large numbers in a method similar to a Twitter account. This has proven to be both a blessing and a curse for Telegram and its users, since these channels can be used for both good and ill. Right now, as Wired reports, the app is a key way for Ukrainians to receive updates from the government during the invasion. "The inflation fire was already hot and now with war-driven inflation added to the mix, it will grow even hotter, setting off a scramble by the world’s central banks to pull back their stimulus earlier than expected," Chris Rupkey, chief economist at FWDBONDS, wrote in an email. "A spike in inflation rates has preceded economic recessions historically and this time prices have soared to levels that once again pose a threat to growth." Either way, Durov says that he withdrew his resignation but that he was ousted from his company anyway. Subsequently, control of the company was reportedly handed to oligarchs Alisher Usmanov and Igor Sechin, both allegedly close associates of Russian leader Vladimir Putin.
from us
