Merge branch 'master' of https://github.com/EleutherAI/lm-evaluation-harness

lm_eval/evaluator.py

 import collections
 import itertools
-import pathlib
+import numpy as np
 import random
 import lm_eval.metrics
 import lm_eval.models
 import lm_eval.tasks
 import lm_eval.base
-import lm_eval.decontamination
-import numpy as np
 from lm_eval.utils import positional_deprecated, run_task_tests
-from lm_eval.decontamination.decontaminate import get_train_overlap
 
 
 @positional_deprecated
@@ -229,6 +226,8 @@ def evaluate(
 
     # Compare all tasks/sets at once to ensure a single training set scan
     if decontaminate:
+        from lm_eval.decontamination.decontaminate import get_train_overlap
+
         print("Finding train/test overlap, please wait...")
         overlaps = get_train_overlap(
             docs_for_decontamination, decontamination_ngrams_path, limit

scripts/clean_training_data/janitor_util.cpp

@@ -176,7 +176,7 @@ clean_ngram_with_indices(std::string const &input, std::string const &ignore,
       }
 
       // Skip ignored characters
-    } else if (ignore.find(*iter) != std::string::npos) {
+    } else if (ignore.find(ch) != std::string::npos) {
       continue;
 
       // If it is a non-ignored character, add it to the ngram and update the