Skip to content

Instantly share code, notes, and snippets.

@iarroyof
iarroyof / train_glove.sh
Created July 26, 2018 18:40
Bash script for creating Glove word embeddings chrashes my hard disk for -vector-size >= 300
#!/bin/bash
set -e
# Makes programs, downloads sample data, trains a GloVe model, and then evaluates it.
# One optional argument can specify the language used for eval script: matlab, octave or [default] python
# Default configuration:
# dimensions: 100, minimum_word_frequency: 1, window: 8 and number_of_threads: 20.
#
# bash train_glove.sh -i $DATA/GUsDany/corpus/GUs_literature.txt\
# -o $DATA/vectors_H100_W8 -s 100 -m 1 -w 8 -t 20