Router-Tuning: A Simple and Effective Approach for Enabling Dynamic-Depth in Transformers
Paper
•
2410.13184
•
Published
•
3
Shwai He
Shwai
AI & ML interests
Deep Learning, Mechine Learning, Natural Language Processing.
Recent Activity
upvoted
a
paper
about 17 hours ago
Router-Tuning: A Simple and Effective Approach for Enabling
Dynamic-Depth in Transformers
upvoted
a
paper
1 day ago
Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of
Experts
commented on
a paper
1 day ago
Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of
Experts
Organizations
Shwai's activity
upvoted
a
paper
about 17 hours ago
upvoted
a
paper
1 day ago
commented
a
paper
1 day ago
upvoted
2
papers
about 1 month ago
liked
14
models
5 months ago
s1ghhh/Mistral-7B-v0.1-Drop4Attn
Updated
•
8
•
2
s1ghhh/Llama-2-13b-Drop8Block
Updated
•
8
•
2
s1ghhh/Llama-2-13b-Drop4Block
Updated
•
11
•
2
s1ghhh/Llama-2-13b-Drop8Attn
Updated
•
12
•
2
s1ghhh/Llama-2-13b-Drop4Attn
Updated
•
7
•
2
s1ghhh/Llama-2-13b-Drop4MLP
Updated
•
8
•
2
s1ghhh/Llama-2-13b-Drop8MLP
Updated
•
15
•
2
s1ghhh/Mistral-7B-v0.1-Drop4Block
Updated
•
10
•
2
s1ghhh/Mistral-7B-v0.1-Drop8Block
Updated
•
7
•
2
s1ghhh/Mistral-7B-v0.1-Drop8Attn
Updated
•
13
•
2
s1ghhh/Mistral-7B-v0.1-Drop4MLP
Updated
•
9
•
2
s1ghhh/Mistral-7B-v0.1-Drop8MLP
Updated
•
9
•
2
s1ghhh/Llama-3-70b-Drop
Text Generation
•
Updated
•
10
•
3
s1ghhh/Llama-2-70b-Drop
Text Generation
•
Updated
•
14
•
2
authored
a
paper
5 months ago