Loading tools/openwebtext/group_duplicate_url.py +1 −1 Original line number Diff line number Diff line Loading @@ -19,7 +19,7 @@ import sys def is_similar(jaccard_similarity): return (js >= 0.9) return (jaccard_similarity >= 0.7) if __name__ == '__main__': Loading Loading
tools/openwebtext/group_duplicate_url.py +1 −1 Original line number Diff line number Diff line Loading @@ -19,7 +19,7 @@ import sys def is_similar(jaccard_similarity): return (js >= 0.9) return (jaccard_similarity >= 0.7) if __name__ == '__main__': Loading