graham
besiktas
AI & ML interests
None yet
Recent Activity
liked
a model
5 days ago
SparkAudio/Spark-TTS-0.5B
updated
a model
9 months ago
besiktas/clippy-pali
updated
a model
11 months ago
besiktas/fuyu-8b
Organizations
None yet
besiktas's activity
Has anyone tried adding positional embeddings to the image patches to improve the model?
2
#70 opened 12 months ago
by
jchiu1234
Reason for using PerceiverResampler/Cross-Attention/IDEFICS related modality layers?
3
#3 opened about 1 year ago
by
besiktas
Are there special tokens that are ignored during loss computation?
9
#62 opened over 1 year ago
by
Nyandwi

Here is a simple multimodal like training script to see model working.
3
#60 opened over 1 year ago
by
besiktas
fine-tuning using FSDP and non 80GB cards?
8
#43 opened over 1 year ago
by
besiktas
fine-tuning using FSDP and non 80GB cards?
8
#43 opened over 1 year ago
by
besiktas
fine-tuning using FSDP and non 80GB cards?
8
#43 opened over 1 year ago
by
besiktas