QA Roberta Ru SaaS
Question answering on russian with XLMRobertaLarge as a service. Thanks for the model to Alexander Kaigorodov.
Stack
- Flask
- Gunicorn
Build image
sudo docker build . --tag qa-roberta-ru-saas
Run on CPU and predict
sudo docker run --rm -p 8080:8080 --name qa-roberta-ru-saas qa-roberta-ru-saas
curl -H "Content-Type: application/json" --data @tests/app/data/test_input.json 0.0.0.0:8080/predict
Run on GPU
Change device to cuda:0 in config before docker build:
device: cuda:0
After build:
sudo docker run --rm --gpus 0 -p 8080:8080 --name qa-roberta-ru-saas qa-roberta-ru-saas
To run with restart:
sudo docker run --gpus 0 -p 8080:8080 --restart always --name qa-roberta-ru-saas qa-roberta-ru-saas
To stop it later:
docker update --restart unless-stopped qa-roberta-ru-saas
To run tests:
pytest tests/
To run app without docker container
PYTHONPATH=. python app/app_main.py
TODO:
- GPU/CPU support
- Support of context longer than 512 bpe
- Predict on long context with sliding window
3.6k Jan 07, 2023
13 Aug 27, 2022
1.2k Jan 01, 2023
33 Dec 05, 2022
98 Jan 07, 2023
5 Nov 11, 2022
13 Dec 09, 2022
0 Sep 25, 2022
3 Jan 29, 2022
59 Oct 10, 2022
2 Dec 14, 2022
9 Jan 07, 2023
5 Dec 11, 2022
1.8k Dec 31, 2022
1 Jan 06, 2022
4 Aug 21, 2022
146 Dec 18, 2022
13 Nov 05, 2021
1 Feb 10, 2022
18 Dec 19, 2022