Two variants of dataset are available in separate files:
|pl-embeddings-cbow.txt||2016-01-04 23:22||855M||generated using continuous-bag-of-words method|
|pl-embeddings-skip.txt||2016-01-04 23:24||854M||generated using skip-gram method|
The first line of each dataset contains two numbers: number of words in a dictionary and a number of dimensions of the word embeddings.
The following lines contain the word and space-separated list of numbers that form the word embedding.