Downloads · 30 days
0
mia-project-2025/T5-base-feature-extraction-natural-questions-shortQA
T5-base-feature-extraction-natural-questions-shortQA is a machine learning model from mia-project-2025. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This repository contains a T5-base model fine-tuned using feature-based transfer learning on the Natural Questions ShortQA dataset to answer short-form questions given a context passage.
Downloads · 30 days
0
Access
Public
Updated Aug 24, 2025
Repo size
3.6 GB
Likes
0
Public
Click a slice to open those files.
.pt1.8 GB · 50%
From the Hugging Face model README
This repository contains a T5-base model fine-tuned using feature-based transfer learning on the Natural Questions ShortQA dataset to answer short-form questions given a context passage.
lucadiliello/naturalquestionsshortqa (80/20 train/test split)mrm8488/t5-base-finetuned-squadv2| Metric | Score (%) |
|---|---|
| Exact Match (EM) | 68.02 |
| F1 Score | 77.85 |
Results are after 15 epochs of feature-based fine-tuning on GPU with frozen encoder.