nevmenandr's picture
Update README.md
927dc71 verified
|
raw
history blame
1.15 kB
metadata
license: mit
tags:
  - natural-language-processing
  - code-generation
  - torch
  - lstm

This generative text model was trained using Andrej Karpathy's code on homeworks by Linguistics students' homework assignments for a beginning Python course of HSE University.

Model was trained with size 512 and 3 layers, dropout 0.5.

Usage

The procedure for installing the required software is described by Karpathy, torch is required, the code is written in lua. Be careful, versions of libraries written many years ago are used.

th sample.lua lm_lstm_epoch19.14_0.6292.t7 -length 10000 -temperature 0.5 -primetext 'some text' 

Train data

Train corpus consists of joined programms in to one file inclded in this repository as input.txt

What for?

In an era of winning Transformers, ancient RNN models seem archaic. But I see that they still work better than modern architectures with such important categories from the humanities point of view as individual style.

This model was created just or fun of students at the end of the course.