OpenMOSS-Team
/

MOSS-VL-Base-0408

Video-Text-to-Text

feature-extraction

Video-Understanding

Image-Understanding

vision-language

Model card Files Files and versions

Update code for transformers 5.5.4

#5

by sjzhou - opened 20 days ago

base: refs/heads/main

←

from: refs/pr/5

Discussion Files changed

Files changed (1) hide show

preprocessor_config.json +3 -3

preprocessor_config.json CHANGED Viewed

@@ -1,13 +1,13 @@
 {
     "auto_map": {
         "AutoProcessor": "processing_moss_vl.MossVLProcessor",
-        "AutoImageProcessor": "processing_moss_vl.MossVLImageProcessorFast"
     },
     "size": {
         "longest_edge": 16777216,
         "shortest_edge": 4096
     },
-    "multi_image_max_pixels": 201326592,
     "patch_size": 16,
     "temporal_patch_size": 1,
     "merge_size": 2,
@@ -22,5 +22,5 @@
         0.5
     ],
     "processor_class": "MossVLProcessor",
-    "image_processor_type": "MossVLImageProcessorFast"
 }

 {
     "auto_map": {
         "AutoProcessor": "processing_moss_vl.MossVLProcessor",
+        "AutoImageProcessor": "processing_moss_vl.MossVLImageProcessor"
     },
     "size": {
         "longest_edge": 16777216,
         "shortest_edge": 4096
     },
+    "multi_image_max_pixels": 65536000,
     "patch_size": 16,
     "temporal_patch_size": 1,
     "merge_size": 2,
         0.5
     ],
     "processor_class": "MossVLProcessor",
+    "image_processor_type": "MossVLImageProcessor"
 }