Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Ifeval: Dowload punkt_tab on rank 0 #2267

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Ifeval: Dowload punkt_tab on rank 0 #2267

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f611817
download nltk `punkt_tab` on LOCAL_RANK=0
baberabb Aug 30, 2024
5e89982
remove print
baberabb Aug 30, 2024
8a78ea2
remove `time`
baberabb Sep 19, 2024
f691592
nit
baberabb Sep 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 9 additions & 5 deletions lm_eval/tasks/ifeval/instructions_util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,33 +15,37 @@
"""Utility library of instructions."""

import functools
import os
import random
import re
from importlib.metadata import version

import immutabledict
import nltk
import pkg_resources
from packaging import version
from packaging.version import parse as parse_version


# Downloading 'punkt' with nltk<3.9 has a remote code vuln.
# see https://github.com/EleutherAI/lm-evaluation-harness/issues/2210
# and https://github.com/nltk/nltk/issues/3266
# for more information.
NLTK_MIN_VERSION = "3.9.1"
RANK = os.environ.get("LOCAL_RANK", "0")


def download_nltk_resources():
"""Download 'punkt' if not already installed"""
nltk_version = pkg_resources.get_distribution("nltk").version
assert (
version.parse(nltk_version) >= version.parse(NLTK_MIN_VERSION)
(nltk_version := parse_version(version("nltk")))
>= parse_version(NLTK_MIN_VERSION)
), f"`nltk` version {nltk_version} is not >= {NLTK_MIN_VERSION}. Please update `nltk` before proceeding--older versions are vulnerable to a remote code execution vulnerability."

try:
nltk.data.find("tokenizers/punkt_tab")
except LookupError:
nltk.download("punkt_tab")
if RANK == "0":
nltk.download("punkt_tab")
print("Downloaded punkt_tab on rank 0")


download_nltk_resources()
Expand Down
Loading