https://github.com/deeppavlov/stand_squad_en
https://github.com/deeppavlov/stand_squad_en
Last synced: 10 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/deeppavlov/stand_squad_en
- Owner: deeppavlov
- Created: 2018-02-15T12:19:01.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2018-04-05T09:41:54.000Z (over 8 years ago)
- Last Synced: 2025-01-05T19:22:10.926Z (over 1 year ago)
- Language: Python
- Size: 45.9 KB
- Stars: 1
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Demo stand. Model: SQuAD (English)
## Installation and start
1. Clone the repo and `cd` to project root:
```
git clone https://github.com/deepmipt/stand_squad_en.git
cd stand_squad_en
```
2. Run script to download and unpack model components:
```
./download_components.sh
```
3. Create a virtual environment with `Python 3.6`:
```
virtualenv env -p python3.6
```
4. Activate the environment:
```
source ./env/bin/activate
```
5. Install requirements:
```
pip install -r requirements.txt
```
6. Download NLTK data:
```
$ python3
>>> import nltk
>>> nltk.download('punkt')
```
7. Specify model endpoint host (`api_host`) and port (`api_port`) in `squad_agent_config.json`
8. Specify `CUDA_VISIBLE_DEVICES` and virtual environment path (if necessary) in `run_en_squad.sh`
9. Run model:
```
./run_en_squad.sh
```
## Building and running with Docker:
1. If necessary, build Base Docker image from:
https://github.com/deepmipt/stand_docker_cuda
2. Clone the repo and `cd` to project root:
```
git clone https://github.com/deepmipt/stand_squad_en.git
cd stand_squad_en
```
3. Build Docker image:
```
sudo docker build -t stand/squad_en .
```
4. Run Docker image:
```
sudo docker run -p :6008 --runtime=nvidia --device=/dev/nvidia -v :/logs stand/squad_en
```