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
I run the LLAVA-34B model in one single A800(80GB) GPU. The inputs are some multi-modal math word problems(like those in MATH), but it turns out that each sample takes more than 1 minute.
I set do_sample=False and max_new_tokens=2048.
The text was updated successfully, but these errors were encountered:
Describe the issue
I run the LLAVA-34B model in one single A800(80GB) GPU. The inputs are some multi-modal math word problems(like those in MATH), but it turns out that each sample takes more than 1 minute.
I set do_sample=False and max_new_tokens=2048.
The text was updated successfully, but these errors were encountered: