Downloads · 30 days
11
1% of all-time downloads
distilt5-qg-hl-12-6
valhalla/distilt5-qg-hl-12-6
distilt5-qg-hl-12-6 is a machine learning model from valhalla. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
This is distilled version of t5-base-qg-hl model trained for answer aware question generation task. The answer spans are highlighted within the text with special highlight tokens.
All-time downloads
1.7K
Public
Repo size
1.3 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin665 MB · 100%
At a glance
- Library
- transformers
- License
- mit
- Model type
- t5
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Sep 23, 2021
- SHA
- 16c582cf
Try a prompt
Datasets
Model card
From the Hugging Face model README
DistilT5 for question-generation
This is distilled version of t5-base-qg-hl model trained for answer aware question generation task. The answer spans are highlighted within the text with special highlight tokens.
The model is distilled using the No Teacher Distillation method proposed by Huggingface, here.
We just copy alternating layers from t5-base-qg-hl and finetune more on the same data. Following table lists other distilled models and their metrics.
| Name | BLEU-4 | METEOR | ROUGE-L | QA-EM | QA-F1 |
|---|---|---|---|---|---|
| distilt5-qg-hl-6-4 | 18.4141 | 24.8417 | 40.3435 | - | - |
| distilt5-qa-qg-hl-6-4 | 18.6493 | 24.9685 | 40.5605 | 76.13 | 84.659 |
| distilt5-qg-hl-12-6 | 20.5275 | 26.5010 | 43.2676 | - | - |
| distilt5-qa-qg-hl-12-6 | 20.6109 | 26.4533 | 43.0895 | 81.61 | 89.831 |
You can play with the model using the inference API, just highlight the answer spans with <hl> tokens. For example
<hl> 42 <hl> is the answer to life, the universe and everything.
For more deatils see this repo.
Model in action 🚀
You'll need to clone the repo.
from pipelines import pipeline
nlp = pipeline("question-generation", model="valhalla/distilt5-qg-hl-12-6")
nlp("42 is the answer to life, universe and everything.")
=> [{'answer': '42', 'question': 'What is the answer to life, the universe and everything?'}]
- Library
- transformers
- Type
- t5
- License
- mit
- Created
- Mar 2, 2022
- Updated
- Sep 23, 2021