preprocessing part
talrose01 opened this issue · comments
tal rosentzweig commented
We want to know which path did you replace at in preprocess_embedding.sh with real path?
thanks
vedarddy commented
Did you figure out which path works?
Saren Arterius commented
For people who are lost, you are supposed to download a 2GB (unzipped 5GB) labels: https://nlp.stanford.edu/projects/glove/ Common Crawl (840B tokens, 2.2M vocab, cased, 300d vectors, 2.03 GB download): glove.840B.300d.zip
adrien-jacquot commented
Would be nice to add this part in the readme