Johnathan Chiu

jchiu1234's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

New activity in adept/fuyu-8b 5 months ago

Has anyone tried adding positional embeddings to the image patches to improve the model?

1

#70 opened 5 months ago by jchiu1234

Masking the image tokens during training

#68 opened 5 months ago by jchiu1234