DoRA: Weight-Decomposed Low-Rank Adaptation

  Рет қаралды 2,104

Gabriel Mongaras

Gabriel Mongaras

Күн бұрын

Paper: arxiv.org/abs/...
My notes: drive.google.c...

Пікірлер: 7
@dankkush5678
@dankkush5678 8 ай бұрын
Great video man so many people just do low effort while you actually explain
@tommyshelby6277
@tommyshelby6277 2 ай бұрын
best video out there!
@tamominh1604
@tamominh1604 9 ай бұрын
insane video bro!
@thisismambonumber5
@thisismambonumber5 4 ай бұрын
this video was so cool thanks ❤ i know its diffusion model specific but it would be cool if you could explain lycoris like this
@pastuh
@pastuh 9 ай бұрын
Is there a possibility to improve model without overwriting existing data?
@lonlynight8616
@lonlynight8616 Ай бұрын
noice
@tankieslayer6927
@tankieslayer6927 9 ай бұрын
Nice 👍
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
35:52
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
Gabriel Mongaras
Рет қаралды 2,8 М.
LoRA explained (and a bit about precision and quantization)
17:07
LoRA explained (and a bit about precision and quantization)
DeepFindr
Рет қаралды 66 М.
Noodles Eating Challenge, So Magical! So Much Fun#Funnyfamily #Partygames #Funny
00:33
Noodles Eating Challenge, So Magical! So Much Fun#Funnyfamily #Partygames #Funny
Family Games Media
Рет қаралды 70 МЛН
FOREVER BUNNY
00:14
FOREVER BUNNY
Natan por Aí
Рет қаралды 33 МЛН
Yay😃 Let's make a Cute Handbag for me 👜 #diycrafts #shorts
00:33
Yay😃 Let's make a Cute Handbag for me 👜 #diycrafts #shorts
LearnToon - Learn & Play
Рет қаралды 117 МЛН
ТЮРЕМЩИК В БОКСЕ! #shorts
00:58
ТЮРЕМЩИК В БОКСЕ! #shorts
HARD_MMA
Рет қаралды 2,7 МЛН
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
40:14
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Gabriel Mongaras
Рет қаралды 2,1 М.
Stable Diffusion 3: Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
1:02:30
Stable Diffusion 3: Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
Gabriel Mongaras
Рет қаралды 4,6 М.
Simply explained! KAN: Kolmogorov-Arnold Networks is interpretable! Mathematics and Physics
6:47
Simply explained! KAN: Kolmogorov-Arnold Networks is interpretable! Mathematics and Physics
Bin Yiu
Рет қаралды 12 М.
xLSTM: Extended Long Short-Term Memory
43:26
xLSTM: Extended Long Short-Term Memory
Gabriel Mongaras
Рет қаралды 2 М.
Norway Sovereign Wealth Fund's Investment Philosophy
12:47
Norway Sovereign Wealth Fund's Investment Philosophy
Bloomberg Television
Рет қаралды 74 М.
Dr Gabor Mate answers question about October 7th during conference
12:53
Dr Gabor Mate answers question about October 7th during conference
Middle East Eye
Рет қаралды 505 М.
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits and BitNet
46:25
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits and BitNet
Gabriel Mongaras
Рет қаралды 6 М.
Deterministic Image Editing with DDPM Inversion, DDIM Inversion, Null Inversion and Prompt-to-Prompt
1:13:10
Deterministic Image Editing with DDPM Inversion, DDIM Inversion, Null Inversion and Prompt-to-Prompt
Gabriel Mongaras
Рет қаралды 1,4 М.
Low-rank Adaption of Large Language Models: Explaining the Key Concepts Behind LoRA
19:17
Low-rank Adaption of Large Language Models: Explaining the Key Concepts Behind LoRA
Chris Alexiuk
Рет қаралды 111 М.
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
32:49
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
Gabriel Mongaras
Рет қаралды 3,7 М.
Noodles Eating Challenge, So Magical! So Much Fun#Funnyfamily #Partygames #Funny
00:33
Noodles Eating Challenge, So Magical! So Much Fun#Funnyfamily #Partygames #Funny
Family Games Media
Рет қаралды 70 МЛН