model: support Step3V (#8583)

Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: nnnobody-code <nnnobody@foxmail.com>
Co-authored-by: ispobock <ispobaoke@gmail.com>
Co-authored-by: Qiaolin-Yu <qy254@cornell.edu>
Co-authored-by: Qiaolin-Yu <liin1211@outlook.com>
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
This commit is contained in:
Chang Su
2025-07-31 02:41:00 -07:00
committed by GitHub
parent 09f1a247ce
commit 51c38163c1
16 changed files with 2340 additions and 23 deletions

View File

@@ -176,6 +176,8 @@ class BaseMultimodalProcessor(ABC):
"image_grid_hws": Modality.IMAGE,
"aspect_ratio_ids": Modality.IMAGE,
"aspect_ratio_mask": Modality.IMAGE,
"num_patches": Modality.IMAGE,
"patch_pixel_values": Modality.IMAGE,
# Audio-related attributes
"audio_features": Modality.AUDIO,
"audio_feature_lens": Modality.AUDIO,