moka-ai
/

m3e-base

sentence-transformers

Model card Files Files and versions

请问加载模型后产出embedding很慢有什么办法么？

#15

by EEik - opened Jul 26, 2023

使用model.encode处理长度约为几十万的string list，预估速度很慢

Moka HR SaSS org Jul 26, 2023

从 pytorch 实现转为 ONNX，参考这个讨论 [https://huggingface.co/moka-ai/m3e-base/discussions/12#64bf9ebaa0e547106693129c]
加机器，加 GPU ，从硬件角度来提升速度

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment