Giters
mlpen
/
Nystromformer
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
359
Watchers:
9
Issues:
18
Forks:
41
mlpen/Nystromformer Issues
Does it support causal mask for GPT2-esque models?
Updated
a year ago
Comments count
7
Max length for text task
Updated
a year ago
LRA cifar10.py never stop
Updated
2 years ago
Please add a license to this repo
Updated
2 years ago
Self-attention weights don't always sum to 1
Updated
2 years ago
Comments count
2
score of softmax on Text4k; linformer-256 & nystrom-64 doesn't work
Updated
2 years ago
Comments count
1
Pre-trained weights
Closed
3 years ago
Comments count
6
Length of Text Classification Task of LRA
Closed
3 years ago
Comments count
2
Question about LRA Pathfinder task
Closed
3 years ago
Comments count
2
Retrieval accuracy different from official JAX/FLAX implementation
Updated
3 years ago
Comments count
1
Preprocessing datasets
Closed
3 years ago
Comments count
3
Some questions regarding the paper
Closed
3 years ago
Comments count
1
Incorrect initialization of pseudoinverse matrix calculation leads to convergence failure
Updated
3 years ago
Comments count
11
stories dataset for plm
Closed
3 years ago
Comments count
1
Influence of the "conv_kernel_size" within the proposed Nystrom Attention
Updated
3 years ago
Comments count
4
Possible bug in iterative_inv
Closed
3 years ago
Comments count
6
Lemma 1 parenthesis seem wrong
Closed
4 years ago
Comments count
3
Results on Long Range Arena
Closed
4 years ago
Comments count
3