Fartash Faghri
fartashf
AI & ML interests
None yet
Recent Activity
authored
a paper
5 days ago
FastVLM: Efficient Vision Encoding for Vision Language Models
new activity
about 2 months ago
apple/DataCompDR-12M:Is there a method to prepare one's own dataset and finetune mobileclip?
Organizations
fartashf's activity
Is there a method to prepare one's own dataset and finetune mobileclip?
3
#2 opened 4 months ago
by
oatmeal3000
Why the size of text_emb is 7, not 6 in your npz file?
1
#4 opened 2 months ago
by
Hao-HUST
How to get the images?
6
#3 opened 2 months ago
by
guanqi
Issue with Training Model Using DataCompDR Dataset in open_clip
10
#4 opened 5 months ago
by
jihwaneom
Unable to Download Specific Files from DataCompPR-12M-bf16 Dataset
4
#3 opened 5 months ago
by
jihwaneom
License text?
1
#4 opened 5 months ago
by
Li0ness
Ground truth txt label
3
#1 opened 7 months ago
by
Alexislhb
Upload fig_accuracy_latency.png
#2 opened 7 months ago
by
reach-vb
How to Use this Model for Zero-Shot Image Classification?
2
#2 opened 6 months ago
by
eclipticwonder
Usage of Image Augmentation Parameters
3
#2 opened 7 months ago
by
Alexislhb
Issue when downloading the data via streaming
5
#3 opened 7 months ago
by
mrdbourke
Update README.md
#1 opened 7 months ago
by
merve
Update README.md
#1 opened 7 months ago
by
merve
Update README.md
#1 opened 7 months ago
by
merve
Update README.md
#1 opened 7 months ago
by
merve
Update README.md
#1 opened 7 months ago
by
merve
add library
#1 opened 7 months ago
by
merve
small metadata suggestions
#2 opened 7 months ago
by
davanstrien
Usage of Image Augmentation Parameters
3
#2 opened 7 months ago
by
Alexislhb