How DeepSeek Changes the LLM Story

  Рет қаралды 11,210

Sasha Rush

Sasha Rush

Күн бұрын

Quick turnaround survey of DeepSeek v3 and DeepSeek R1 the two technical papers behind the recent open-source LLM news. Presented at Simons Institute Feb 3, 2024.
Slides: docs.google.co...

Пікірлер: 19
DeepSeek facts vs hype, model distillation, and open source competition
39:17
DeepSeek facts vs hype, model distillation, and open source competition
IBM Technology
Рет қаралды 108 М.
Speculations on Test-Time Scaling (o1)
47:56
Speculations on Test-Time Scaling (o1)
Sasha Rush 🤗
Рет қаралды 25 М.
😯 Подарила сыну БМВ, но не ожидала такой реакции на машину! | Новостничок
00:20
😯 Подарила сыну БМВ, но не ожидала такой реакции на машину! | Новостничок
НОВОСТНИЧОК
Рет қаралды 6 МЛН
IL'HAN - Qalqam | Official Music Video
03:17
IL'HAN - Qalqam | Official Music Video
Ilhan Ihsanov
Рет қаралды 700 М.
伪装成一棵树整蛊妹妹，结果妹妹当场怀疑人生竟要揍我？【两只马儿-恶搞姐妹】
00:57
伪装成一棵树整蛊妹妹，结果妹妹当场怀疑人生竟要揍我？【两只马儿-恶搞姐妹】
两只马儿—恶搞姐妹
Рет қаралды 44 МЛН
Леон киллер и Оля Полякова 😹
00:42
Леон киллер и Оля Полякова 😹
Канал Смеха
Рет қаралды 4,7 МЛН
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
57:45
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
Grant Sanderson
Рет қаралды 439 М.
What if all the world's biggest problems have the same solution?
24:52
What if all the world's biggest problems have the same solution?
Veritasium
Рет қаралды 1,6 МЛН
NVIDIA CEO Jensen Huang's Vision for the Future
1:03:03
NVIDIA CEO Jensen Huang's Vision for the Future
Cleo Abram
Рет қаралды 1,3 МЛН
[1hr Talk] Intro to Large Language Models
59:48
[1hr Talk] Intro to Large Language Models
Andrej Karpathy
Рет қаралды 2,5 МЛН
Will Merrill: The Illusion of State in State-Space Models
45:43
Will Merrill: The Illusion of State in State-Space Models
Formal Languages and Neural Networks Seminar
Рет қаралды 1,8 М.
How China’s New AI Model DeepSeek Is Threatening U.S. Dominance
40:25
How China’s New AI Model DeepSeek Is Threatening U.S. Dominance
CNBC
Рет қаралды 5 МЛН
Terence Tao on how we measure the cosmos | Part 1
28:33
Terence Tao on how we measure the cosmos | Part 1
3Blue1Brown
Рет қаралды 880 М.
Stanford Webinar - Large Language Models Get the Hype, but Compound Systems Are the Future of AI
58:06
Stanford Webinar - Large Language Models Get the Hype, but Compound Systems Are the Future of AI
Stanford Online
Рет қаралды 113 М.
Global Capitalism: What Trump 2.0 Means
1:02:56
Global Capitalism: What Trump 2.0 Means
Democracy At Work
Рет қаралды 2,5 МЛН
Attention in transformers, step-by-step | DL6
26:10
Attention in transformers, step-by-step | DL6
3Blue1Brown
Рет қаралды 2,2 МЛН
😯 Подарила сыну БМВ, но не ожидала такой реакции на машину! | Новостничок
00:20
😯 Подарила сыну БМВ, но не ожидала такой реакции на машину! | Новостничок
НОВОСТНИЧОК
Рет қаралды 6 МЛН