This repository contains scripts, notebooks, data, and a report from a project exploring the effects of transformer model distillation on the question answering task. In particular, we fine-tune BERT, RoBERTa, distilBERT, and distilRoBERTa on the Stanford Question Answering Dataset (SQuAD) and compare model performance, model training time, and model inference time.
-
Notifications
You must be signed in to change notification settings - Fork 0
mukund-v/distil-on-squad
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Exploring the effects of transformer model distillation on Q/A performance and efficiency.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published