You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, some minor issue is observed. CLIP has a context length of up to 77 tokens, and this is not properly handled. If the input exceeds 77 tokens, an error occurs in yolo world model. Do you think this issue is due to Hugging Face's implementation, or can it be fixed within the YOLO-World codebase?
Thanks
The text was updated successfully, but these errors were encountered:
Hi, some minor issue is observed. CLIP has a context length of up to 77 tokens, and this is not properly handled. If the input exceeds 77 tokens, an error occurs in yolo world model. Do you think this issue is due to Hugging Face's implementation, or can it be fixed within the YOLO-World codebase?
Thanks
The text was updated successfully, but these errors were encountered: