search

marksverdhei / bert-bot

Discord bot
GNU General Public License v3.0
5 stars 2 forks source link

Use quantization/pruning #8

Open marksverdhei opened 2 years ago

marksverdhei commented 2 years ago

Reduce neural network size by pruning and quantization for better performance

marksverdhei commented 2 years ago

We can for instance use HuggingFace optimum: https://github.com/huggingface/optimum