bfshi scaling_on_scales issues - Githubissues

bfshi / scaling_on_scales

When do we not need larger vision models?

MIT License

340 stars 11 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Added einops for readability

#17 mawanda-jun opened 5 days ago
2
fix typo

#16 cosmos1030 closed 2 weeks ago
0
Potential information loss

#15 GeneZC closed 3 weeks ago
2
About Vstar Evaluation

#14 jungle-gym-ac opened 5 months ago
6
How to infer Llava with S^2?

#13 Gumpest opened 5 months ago
3
How to train Llava with S^2?

#12 Chloe1997 opened 5 months ago
1
Question about the VIT baseline for imagenet classification

#11 mingkai-zheng closed 5 months ago
4
About the choices in LLaVA+S^2 implementation

#10 jungle-gym-ac opened 6 months ago
2
Hello, nice work, just wonder if used s2 in llava, will the vit can be trained?

#9 MonolithFoundation opened 6 months ago
3
Why the res is 1008 in paper?

#8 OpenJarvisAI opened 7 months ago
1
How to add multiscale_forward functionality to my model

#7 1chenchen22 opened 8 months ago
15
About non-square input

#6 githubiubiu opened 8 months ago
4
Questions about paper

#5 JihwanEom opened 8 months ago
1
Num of tokens in LLaVA

#4 RussRobin closed 8 months ago
3
Any plan to release pre-trained weights?

#3 JihwanEom opened 8 months ago
2
More Bench？

#2 BlueBlueFF closed 8 months ago
1
Can you use this with SAM?

#1 jetjodh closed 8 months ago
1