Telegram Group & Telegram Channel
⭐️ Simple GRPO

Вы можете запустить GRPO (Group Relative Policy Optimization - основной алгоритм Deepseek r1), для моделей на 8b параметров на GPU стоимостью 10 долл/ч.

4xH100 достаточно для тренировки Llama 3.1 8b и алгоритм прекрасно работает.

Код: https://github.com/minosvasilias/simple_grpo

@data_analysis_ml

#gpro #deepseek #reasoning
Please open Telegram to view this post
VIEW IN TELEGRAM



group-telegram.com/data_analysis_ml/3156
Create:
Last Update:

⭐️ Simple GRPO

Вы можете запустить GRPO (Group Relative Policy Optimization - основной алгоритм Deepseek r1), для моделей на 8b параметров на GPU стоимостью 10 долл/ч.

4xH100 достаточно для тренировки Llama 3.1 8b и алгоритм прекрасно работает.

Код: https://github.com/minosvasilias/simple_grpo

@data_analysis_ml

#gpro #deepseek #reasoning

BY Анализ данных (Data analysis)




Share with your friend now:
group-telegram.com/data_analysis_ml/3156

View MORE
Open in Telegram


Telegram | DID YOU KNOW?

Date: |

Perpetrators of these scams will create a public group on Telegram to promote these investment packages that are usually accompanied by fake testimonies and sometimes advertised as being Shariah-compliant. Interested investors will be asked to directly message the representatives to begin investing in the various investment packages offered. "Markets were cheering this economic recovery and return to strong economic growth, but the cheers will turn to tears if the inflation outbreak pushes businesses and consumers to the brink of recession," he added. But the Ukraine Crisis Media Center's Tsekhanovska points out that communications are often down in zones most affected by the war, making this sort of cross-referencing a luxury many cannot afford. Recently, Durav wrote on his Telegram channel that users' right to privacy, in light of the war in Ukraine, is "sacred, now more than ever." Telegram boasts 500 million users, who share information individually and in groups in relative security. But Telegram's use as a one-way broadcast channel — which followers can join but not reply to — means content from inauthentic accounts can easily reach large, captive and eager audiences.
from it


Telegram Анализ данных (Data analysis)
FROM American