[SUBS]RANK
VIDEOS / LUIS SERRANO ACADEMY / XEUB4H1OO1G

GRPO - Group Relative Policy Optimization - How DeepSeek trains reasoning models

Luis Serrano Academy LUIS SERRANO ACADEMY · SEP 06, 2025

This YouTube video has 14 000 views and was published Sep 6, 2025 on Luis Serrano Academy. That is 0.1x the channel's average views.

GRPO - Group Relative Policy Optimization - How DeepSeek trains reasoning models ▸ WATCH ON YOUTUBE
Views
14 000
Likes
—
Comments
—
Like rate
—
▸ Vs channel average
-86%
This video is at 0.1x the channel's average views.
LAST 13 UPLOADS · ■ THIS VIDEO
Luis Serrano Academy
Luis Serrano Academy
@SerranoAcademy · 196K SUBS · 80 VIDEOS
AUDIT →
More from this channel
Low Rank Adaptation (LoRA) - How to search for a needle in a much smaller haystack Low Rank Adaptation (LoRA) - How to search for a needle in a much smaller haystack 8 700 VIEWS · 2MO AGO The attention mechanism in higher dimensions The attention mechanism in higher dimensions 2 600 VIEWS · 2MO AGO The world's smallest transformer model The world's smallest transformer model 8 200 VIEWS · 2MO AGO The world's smallest attention mechanism The world's smallest attention mechanism 6 900 VIEWS · 2MO AGO