openbmb
/

MiniCPM-V-4_5

Image-Text-to-Text

feature-extraction

document parsing

Model card Files Files and versions

yuzaa commited on about 19 hours ago

Commit

0fe9c69

·

verified ·

1 Parent(s): 0f80664

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -415,7 +415,7 @@ msgs = [
 answer = model.chat(
     msgs=msgs,
     tokenizer=tokenizer,
-    use_image_id=False,
     max_slice_nums=1,
     temporal_ids=frame_ts_id_group
 )

 answer = model.chat(
     msgs=msgs,
     tokenizer=tokenizer,
+    use_image_id=False, # ensure use_image_id=False when video inference
     max_slice_nums=1,
     temporal_ids=frame_ts_id_group
 )