Yazar | SHA1 Mesaj | Tarih |
---|---|---|
AlpinDale | e26a4ac698 chore: avoid loading the unused layers and init the VLM up to the required feature space | 5 ay önce |
AlpinDale | c11a8bdaad fix: calculate max number of multi-modal tokens automatically | 5 ay önce |
AlpinDale | 4599c98f99 feat: dynamic image size support for VLMs | 5 ay önce |
AlpinDale | 3a0fdf7b9b chore: remove `image_input_type` from VLM config | 5 ay önce |
AlpinDale | c0c336aaa3 refactor: registry for processing model inputs; quick_gelu; clip model support | 5 ay önce |