OpenGVLab
/

ScaleCUA-7B

Image-Text-to-Text

text-generation-inference

Model card Files Files and versions

ownerEli commited on Sep 18

Commit

da54968

·

verified ·

1 Parent(s): 4e851ed

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -43,7 +43,7 @@ model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
 min_pixels = 3136
 max_pixels = 2109744
-processor = AutoProcessor.from_pretrained("OpenGVLab/ScaleCUA-3B", min_pixels=min_pixels, max_pixels=max_pixels)
 ````
 ## Direct Action Mode as grounder

 min_pixels = 3136
 max_pixels = 2109744
+processor = AutoProcessor.from_pretrained("OpenGVLab/ScaleCUA-7B", min_pixels=min_pixels, max_pixels=max_pixels)
 ````
 ## Direct Action Mode as grounder