Update utils.py

lm_eval/tasks/truthfulqa/utils.py

@@ -169,49 +169,3 @@ def rouge(refs, preds):
         aggregator.add_scores(scorer.score(ref, pred))
     result = aggregator.aggregate()
     return {type: result[type].mid.fmeasure * 100 for type in rouge_types}
-
-
-# def bleurt_max(predictions, references):
-#     pass
-
-# def bleurt_acc(predictions, references):
-#     pass
-
-# def bleurt_diff(predictions, references):
-#     pass
-
-# def bleu_max(predictions, references):
-#     pass
-
-# def bleu_acc(predictions, references):
-#     pass
-
-# def bleu_diff(predictions, references):
-#     pass
-
-# def rouge1_max(predictions, references):
-#     pass
-
-# def rouge1_acc(predictions, references):
-#     pass
-
-# def rouge1_diff(predictions, references):
-#     pass
-
-# def rouge2_max(predictions, references):
-#     pass
-
-# def rouge2_acc(predictions, references):
-#     pass
-
-# def rouge2_diff(predictions, references):
-#     pass
-
-# def rougeL_max(predictions, references):
-#     pass
-
-# def rougeL_acc(predictions, references):
-#     pass
-
-# def rougeL_diff(predictions, references):
-#     pass