huggingface 的 bigscience/T0pp 要多大内存？

V2EX = way to explore

V2EX 是一个关于分享和探索的地方

For Existing Member Sign In

This topic created in 1088 days ago, the information mentioned may be changed or developed.

python3 -m manifest.api.app \
    --model_type huggingface \
    --model_name_or_path bigscience/T0pp \
    --use_hf_parallelize

执行的这个命令，32G 内存，提示内存不足，想问下大概要多大？

1 replies

coolair

May 5, 2023

找到了：Just to load the model, you will need ~90GB of CPU memory.