Reproducible scaling laws for contrastive language-image learning
Paper
•
2212.07143
•
Published
•
2
Ross Wightman
rwightman
AI & ML interests
Computer vision, transfer learning, semi/self supervised learning, robotics.
Recent Activity
new activity
2 days ago
timm/vit_little_patch16_reg4_gap_256.sbb_in1k:Loss exploding to nan
liked
a model
16 days ago
openai/gpt-oss-20b
liked
a model
16 days ago
openai/gpt-oss-120b
Organizations
authored
4
papers
over 2 years ago
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
Paper
•
2106.10270
•
Published
•
3
LAION-5B: An open large-scale dataset for training next generation image-text models
Paper
•
2210.08402
•
Published
•
4
ResNet strikes back: An improved training procedure in timm
Paper
•
2110.00476
•
Published
•
3