CogVLM chat #421
CogVLM chat
#421
-
|
Does the "cogvlm-chat-v1.1" model understand grounding coordinates? For exampe can i send a prompt like: "In the submitted image, please give a synopsis of the area [[222,304,292,362]]." to CogVLM chat? |
Beta Was this translation helpful? Give feedback.
Answered by
zRzRzRzRzRzRzR
May 11, 2024
Replies: 1 comment 1 reply
-
|
NVM found the response on the Alignment part of the paper. CogVLM chat does not allow bbox as input |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
it is not allow to usethe question like you mention here |
Beta Was this translation helpful? Give feedback.
Answer selected by
zRzRzRzRzRzRzR
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
it is not allow to usethe question like you mention here