SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Fix hashing for deduplication (#17048)

Browse Source
This commit is contained in:
Thomas Wang
2022-05-04 08:40:24 +02:00
committed by GitHub
parent 39f8eafc1b
commit db034660fb
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/research_projects/codeparrot/scripts/preprocessing.py
View File

@@ -1,4 +1,5 @@
import gzip import gzip
import hashlib
import multiprocessing import multiprocessing
import os import os
import shutil import shutil
@@ -13,7 +14,7 @@ from transformers import HfArgumentParser
def get_hash(example): def get_hash(example):
"""Get hash of content field.""" """Get hash of content field."""
return {"hash": hash(example["content"])} return {"hash": hashlib.md5(example["content"].strip().encode("utf-8")).hexdigest()}
def line_stats(example): def line_stats(example):