Support glm4.1v and glm4.5v (#8798)

Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Co-authored-by: Minglei Zhu <mingleizhu1122@gmail.com>
Co-authored-by: Chang Su <csu272@usc.edu>
This commit is contained in:
Binyao Jiang
2025-08-09 00:59:13 -07:00
committed by GitHub
co-authored by Xinyuan Tong Xinyuan Tong Xinyuan Tong zRzRzRzRzRzRzR Minglei Zhu Chang Su
parent faa25df1ae
commit f29aba8c6e
21 changed files with 1584 additions and 19 deletions
@@ -22,13 +22,19 @@ class BaseMultiModalProcessorOutput:
input_text: str
# frames loaded from image, in given order
images: Optional[list[Union[Image.Image, dict]]] = None
images: Optional[list[Union[Image.Image, dict]]] = dataclasses.field(
default_factory=list
)
# videos
videos: Optional[list[Union[torch.Tensor, dict]]] = None
videos: Optional[list[Union[torch.Tensor, dict]]] = dataclasses.field(
default_factory=list
)
# audios
audios: Optional[list[Union[np.ndarray, dict]]] = None
audios: Optional[list[Union[np.ndarray, dict]]] = dataclasses.field(
default_factory=list
)
def organize_results(self) -> List[Tuple[Modality, Any]]:
"""