Есть уже куча примеров какие чудеса кулибины вытворяют с моделькой LLaMa. А вчера чел соорудил подобие Джарвиса, или Алексы, если хотите, прямо у себя в терминале на MacBook M1 Pro.
Причем все работает реалиайм на связке Whisper + LLaMa.
Под капотом: ggml / whisper.cpp / llama.cpp / Core ML STT: Whisper Small LLM: 13B LLaMA
Другой Кулибин начал прикручивать плагины от ChatGPT к опенсоурсной LLaMa. Уже работает text-retrieval плагин, и есть код.
Есть уже куча примеров какие чудеса кулибины вытворяют с моделькой LLaMa. А вчера чел соорудил подобие Джарвиса, или Алексы, если хотите, прямо у себя в терминале на MacBook M1 Pro.
Причем все работает реалиайм на связке Whisper + LLaMa.
Под капотом: ggml / whisper.cpp / llama.cpp / Core ML STT: Whisper Small LLM: 13B LLaMA
Другой Кулибин начал прикручивать плагины от ChatGPT к опенсоурсной LLaMa. Уже работает text-retrieval плагин, и есть код.
Telegram Messenger Blocks Navalny Bot During Russian Election At the start of 2018, the company attempted to launch an Initial Coin Offering (ICO) which would enable it to enable payments (and earn the cash that comes from doing so). The initial signals were promising, especially given Telegram’s user base is already fairly crypto-savvy. It raised an initial tranche of cash – worth more than a billion dollars – to help develop the coin before opening sales to the public. Unfortunately, third-party sales of coins bought in those initial fundraising rounds raised the ire of the SEC, which brought the hammer down on the whole operation. In 2020, officials ordered Telegram to pay a fine of $18.5 million and hand back much of the cash that it had raised. Stocks dropped on Friday afternoon, as gains made earlier in the day on hopes for diplomatic progress between Russia and Ukraine turned to losses. Technology stocks were hit particularly hard by higher bond yields. The Russian invasion of Ukraine has been a driving force in markets for the past few weeks. For example, WhatsApp restricted the number of times a user could forward something, and developed automated systems that detect and flag objectionable content.
from pl
