remove snli and update tests for good tokenizer

textattack/shared/scripts/attack_args.py

@@ -168,14 +168,6 @@ TEXTATTACK_DATASET_BY_MODEL = {
     ),
     "cnn-mr": ("models/classification/cnn/mr", ("rotten_tomatoes", None, "test"),),
     #
-    # Textual entailment models
-    #
-    # BERT models
-    "bert-base-uncased-snli": (
-        ("models/entailment/bert/snli-uncased", 3),
-        ("snli", None, "test", [1, 2, 0]),
-    ),
-    #
     # Text classification models
     #
     "bert-base-uncased-mr": (

textattack/shared/scripts/attack_args_parser.py

@@ -11,8 +11,7 @@ import numpy as np
 import torch
 
 import textattack
-
-from .attack_args import *
+from textattack.shared.scripts.attack_args import *
 
 
 def set_seed(random_seed):
@@ -521,6 +520,7 @@ def parse_dataset_from_args(args):
         dataset = textattack.datasets.HuggingFaceNLPDataset(
             *dataset_args, shuffle=args.shuffle
         )
+        dataset.examples = dataset.examples[args.num_examples_offset :]
     else:
         raise ValueError("Must supply pretrained model or dataset")
     return dataset