works on
knapsack optimization 1mixed precision 1model compression 1post-training quantization 1vision transformers 1

From the 1 of 2 linked papers with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2025

Accelerating Bangla NLP Tasks with Automatic Mixed Precision: Resource-Efficient Training Preserving Model Efficacy

Md Mehrab Hossain Opi, Sumaiya Khan, Moshammad Farzana Rahman

Training models for Natural Language Processing (NLP) requires substantial computational resources and time, posing significant challenges, especially for NLP development in Bangla…