ebooks

Fediverse ebooks bot using neural networks

Usage

First, install Python dependencies with pip install psycopg2 torch transformers datasets Mastodon.py. Currently only Mastodon with PostgreSQL is supported, but it should be easy to add support for other platforms and databases.

Generate the training data from the Mastodon database using python data.py -d 'dbname=test user=postgres password=secret'. You can skip this step if you have training data from another source.

Next, train the network with python train.py, which may take several hours. It's a lot faster when using a GPU. If you need advanced features when training, you can also train using run_clm.py.

Finally, create a Mastodon application for your bot account and run the bot with python bot.py -i mastodon.instance -t access_token -n 'Initial text'. You can create a cron job to run this periodically. Enjoy!

Resources

• https://closeheat.com/blog/pytorch-lstm-text-generation-tutorial

• https://trungtran.io/2019/02/08/text-generation-with-pytorch/

• https://huggingface.co/docs/transformers/training

• https://huggingface.co/blog/how-to-generate

• https://github.com/huggingface/transformers/tree/master/examples/pytorch/language-modeling