DAMO-NLP-SG
/

VideoLLaMA3-7B

Video-Text-to-Text

videollama3_qwen2

text-generation

large-language-model

video-language-model

Model card Files Files and versions

Cyril666 commited on Jan 24, 2025

Commit

cc02ddc

·

verified ·

1 Parent(s): 7e80dfb

Update image_processing_videollama3.py

Files changed (1) hide show

image_processing_videollama3.py +1 -1

image_processing_videollama3.py CHANGED Viewed

@@ -175,7 +175,7 @@ def batched_resize(
 class Videollama3ImageProcessor(BaseImageProcessor):
     r"""
-    Constructs a DAMOVL image processor that dynamically resizes images based on the original images.
     Args:
         do_resize (`bool`, *optional*, defaults to `True`):

 class Videollama3ImageProcessor(BaseImageProcessor):
     r"""
+    Constructs a VideoLLaMA3 image processor that dynamically resizes images based on the original images.
     Args:
         do_resize (`bool`, *optional*, defaults to `True`):