graham
besiktas
AI & ML interests
None yet
Organizations
None yet
besiktas's activity
Has anyone tried adding positional embeddings to the image patches to improve the model?
2
#70 opened 9 months ago
by
jchiu1234
Reason for using PerceiverResampler/Cross-Attention/IDEFICS related modality layers?
3
#3 opened 11 months ago
by
besiktas
Are there special tokens that are ignored during loss computation?
9
#62 opened about 1 year ago
by
Nyandwi
Here is a simple multimodal like training script to see model working.
3
#60 opened about 1 year ago
by
besiktas
fine-tuning using FSDP and non 80GB cards?
8
#43 opened about 1 year ago
by
besiktas
fine-tuning using FSDP and non 80GB cards?
8
#43 opened about 1 year ago
by
besiktas
fine-tuning using FSDP and non 80GB cards?
8
#43 opened about 1 year ago
by
besiktas