Telegram Group & Telegram Channel
🤗Illustrated Reinforcement Learning from Human Feedback (RLHF)

Отличный блог-пост от HuggingFace с разбором RL для файнтюна языковых моделей (webGPT, instructGPT, chatGPT).

А ещё, RLHF теперь официально поддерживается в transformers через библиотеку trl!

P.S. Сейчас все побегут учить свою mini-chatGPT в колабе)

Блог, GitHub



group-telegram.com/abstractDL/186
Create:
Last Update:

🤗Illustrated Reinforcement Learning from Human Feedback (RLHF)

Отличный блог-пост от HuggingFace с разбором RL для файнтюна языковых моделей (webGPT, instructGPT, chatGPT).

А ещё, RLHF теперь официально поддерживается в transformers через библиотеку trl!

P.S. Сейчас все побегут учить свою mini-chatGPT в колабе)

Блог, GitHub

BY AbstractDL




Share with your friend now:
group-telegram.com/abstractDL/186

View MORE
Open in Telegram


Telegram | DID YOU KNOW?

Date: |

For Oleksandra Tsekhanovska, head of the Hybrid Warfare Analytical Group at the Kyiv-based Ukraine Crisis Media Center, the effects are both near- and far-reaching. Such instructions could actually endanger people — citizens receive air strike warnings via smartphone alerts. In 2014, Pavel Durov fled the country after allies of the Kremlin took control of the social networking site most know just as VK. Russia's intelligence agency had asked Durov to turn over the data of anti-Kremlin protesters. Durov refused to do so. It is unclear who runs the account, although Russia's official Ministry of Foreign Affairs Twitter account promoted the Telegram channel on Saturday and claimed it was operated by "a group of experts & journalists." Two days after Russia invaded Ukraine, an account on the Telegram messaging platform posing as President Volodymyr Zelenskiy urged his armed forces to surrender.
from hk


Telegram AbstractDL
FROM American