Я уже недавно писал, что в эпоху LLM регулярки снова стали актуальным инструментом так называемого AI. Regex-in-the-loop как промежуточный вариант между "слепо доверимся черному ящику" и относительно дорогим human-in-the-loop.
ReLLM filters non-matching tokens pre-generation. For each token, ReLLM tests every possible completion against a partial regex. For the potential completions that do not match the pattern, ReLLM masks the logits so that the language model does not generate them.
У меня нет бенчмарков, потому голословно выскажу предположение, что для ряда нехитрых продакшен задач такой нехитрый костыль сильно сократит отставание опенсорсных LLM от великого и могучего OpenAI.
Я уже недавно писал, что в эпоху LLM регулярки снова стали актуальным инструментом так называемого AI. Regex-in-the-loop как промежуточный вариант между "слепо доверимся черному ящику" и относительно дорогим human-in-the-loop.
ReLLM filters non-matching tokens pre-generation. For each token, ReLLM tests every possible completion against a partial regex. For the potential completions that do not match the pattern, ReLLM masks the logits so that the language model does not generate them.
У меня нет бенчмарков, потому голословно выскажу предположение, что для ряда нехитрых продакшен задач такой нехитрый костыль сильно сократит отставание опенсорсных LLM от великого и могучего OpenAI.
BY partially unsupervised
Warning: Undefined variable $i in /var/www/group-telegram/post.php on line 260
But Telegram says people want to keep their chat history when they get a new phone, and they like having a data backup that will sync their chats across multiple devices. And that is why they let people choose whether they want their messages to be encrypted or not. When not turned on, though, chats are stored on Telegram's services, which are scattered throughout the world. But it has "disclosed 0 bytes of user data to third parties, including governments," Telegram states on its website. Telegram users are able to send files of any type up to 2GB each and access them from any device, with no limit on cloud storage, which has made downloading files more popular on the platform. On December 23rd, 2020, Pavel Durov posted to his channel that the company would need to start generating revenue. In early 2021, he added that any advertising on the platform would not use user data for targeting, and that it would be focused on “large one-to-many channels.” He pledged that ads would be “non-intrusive” and that most users would simply not notice any change. WhatsApp, a rival messaging platform, introduced some measures to counter disinformation when Covid-19 was first sweeping the world.
from tw
