Language Model Playground

Neural network based Language Model implemented with PyTorch.

See documentation for more details.

Environment Prerequest

We only use python version 3.8+. You can install python with
```
apt-get install python3.8 python3.8-dev
```
We use PyTorch and thus use CUDA version: 10.0+. This only work if you have Nvidia GPUs. You can install CUDA library with
```
apt-get install nvidia-driver-450
```
We use pipenv to install dependencies. You can install pipenv with
```
pip install pipenv
```

Clone the project from GitHub.

git clone https://github.com/ProFatXuanAll/language-model-playground.git

Change current directory to language-model-playground.
```
cd language-model-playground
```
Install dependencies. We use pipenv to create virtual environment and install dependencies in virtual environment.
```
pipenv install
```
Start the virtual environment created by pipenv.
```
pipenv shell
```
Now you can run any script under lmp.script! For example, you can take a look on chinese poem dataset by running lmp.script.sample_from_dataset
```
python -m lmp.script.sample_from_dataset chinese-poem
```

Beerware license. Anyone used this project must buy ProFatXuanAll a beer if you met him.