代码拉取完成，页面将自动刷新
TextAttack includes pre-trained models for different common NLP tasks. This makes it easier for users to get started with TextAttack. It also enables a more fair comparison of attacks from the literature.
All evaluation results were obtained using textattack eval to evaluate models on their default
test dataset (test set, if labels are available, otherwise, eval/validation set). You can use
this command to verify the accuracies for yourself: for example, textattack eval --model roberta-base-mr.
The LSTM and wordCNN models' code is available in textattack.models.helpers. All other models are transformers
imported from the transformers package. To list evaluate all
TextAttack pretrained models, invoke textattack eval without specifying a model: textattack eval --num-examples 1000.
All evaluations shown are on the full validation or test set up to 1000 examples.
LSTMlstm-ag-news)
datasets dataset ag_news, split test
lstm-imdb)
datasets dataset imdb, split test
lstm-mr)
datasets dataset rotten_tomatoes, split validation
datasets dataset rotten_tomatoes, split test
lstm-sst2)
datasets dataset glue, subset sst2, split validation
lstm-yelp)
datasets dataset yelp_polarity, split test
wordCNNcnn-ag-news)
datasets dataset ag_news, split test
cnn-imdb)
datasets dataset imdb, split test
cnn-mr)
datasets dataset rotten_tomatoes, split validation
datasets dataset rotten_tomatoes, split test
cnn-sst2)
datasets dataset glue, subset sst2, split validation
cnn-yelp)
datasets dataset yelp_polarity, split test
albert-base-v2albert-base-v2-ag-news)
datasets dataset ag_news, split test
albert-base-v2-cola)
datasets dataset glue, subset cola, split validation
albert-base-v2-imdb)
datasets dataset imdb, split test
albert-base-v2-mr)
datasets dataset rotten_tomatoes, split validation
datasets dataset rotten_tomatoes, split test
albert-base-v2-qqp)
datasets dataset glue, subset qqp, split validation
albert-base-v2-rte)
datasets dataset glue, subset rte, split validation
albert-base-v2-snli)
datasets dataset snli, split test
albert-base-v2-sst2)
datasets dataset glue, subset sst2, split validation
albert-base-v2-stsb)
datasets dataset glue, subset stsb, split validationalbert-base-v2-wnli)
datasets dataset glue, subset wnli, split validation
albert-base-v2-yelp)
datasets dataset yelp_polarity, split test
bert-base-uncasedbert-base-uncased-ag-news)
datasets dataset ag_news, split test
bert-base-uncased-cola)
datasets dataset glue, subset cola, split validation
bert-base-uncased-imdb)
datasets dataset imdb, split test
bert-base-uncased-mnli)
datasets dataset glue, subset mnli, split validation_matched
bert-base-uncased-mr)
datasets dataset rotten_tomatoes, split validation
datasets dataset rotten_tomatoes, split test
bert-base-uncased-mrpc)
datasets dataset glue, subset mrpc, split validation
bert-base-uncased-qnli)
datasets dataset glue, subset qnli, split validation
bert-base-uncased-qqp)
datasets dataset glue, subset qqp, split validation
bert-base-uncased-rte)
datasets dataset glue, subset rte, split validation
bert-base-uncased-snli)
datasets dataset snli, split test
bert-base-uncased-sst2)
datasets dataset glue, subset sst2, split validation
bert-base-uncased-stsb)
datasets dataset glue, subset stsb, split validationbert-base-uncased-wnli)
datasets dataset glue, subset wnli, split validation
bert-base-uncased-yelp)
datasets dataset yelp_polarity, split test
distilbert-base-caseddistilbert-base-cased-cola)
datasets dataset glue, subset cola, split validation
distilbert-base-cased-mrpc)
datasets dataset glue, subset mrpc, split validation
distilbert-base-cased-qqp)
datasets dataset glue, subset qqp, split validation
distilbert-base-cased-snli)
datasets dataset snli, split test
distilbert-base-cased-sst2)
datasets dataset glue, subset sst2, split validation
distilbert-base-cased-stsb)
datasets dataset glue, subset stsb, split validationdistilbert-base-uncaseddistilbert-base-uncased-ag-news)
datasets dataset ag_news, split test
distilbert-base-uncased-cola)
datasets dataset glue, subset cola, split validation
distilbert-base-uncased-imdb)
datasets dataset imdb, split test
distilbert-base-uncased-mnli)
datasets dataset glue, subset mnli, split validation_matched
distilbert-base-uncased-mrpc)
datasets dataset glue, subset mrpc, split validation
distilbert-base-uncased-qnli)
datasets dataset glue, subset qnli, split validation
distilbert-base-uncased-rte)
datasets dataset glue, subset rte, split validation
distilbert-base-uncased-stsb)
datasets dataset glue, subset stsb, split validationdistilbert-base-uncased-wnli)
datasets dataset glue, subset wnli, split validation
roberta-baseroberta-base-ag-news)
datasets dataset ag_news, split test
roberta-base-cola)
datasets dataset glue, subset cola, split validation
roberta-base-imdb)
datasets dataset imdb, split test
roberta-base-mr)
datasets dataset rotten_tomatoes, split validation
datasets dataset rotten_tomatoes, split test
roberta-base-mrpc)
datasets dataset glue, subset mrpc, split validation
roberta-base-qnli)
datasets dataset glue, subset qnli, split validation
roberta-base-rte)
datasets dataset glue, subset rte, split validation
roberta-base-sst2)
datasets dataset glue, subset sst2, split validation
roberta-base-stsb)
datasets dataset glue, subset stsb, split validationroberta-base-wnli)
datasets dataset glue, subset wnli, split validation
xlnet-base-casedxlnet-base-cased-cola)
datasets dataset glue, subset cola, split validation
xlnet-base-cased-imdb)
datasets dataset imdb, split test
xlnet-base-cased-mr)
datasets dataset rotten_tomatoes, split validation
datasets dataset rotten_tomatoes, split test
xlnet-base-cased-mrpc)
datasets dataset glue, subset mrpc, split validation
xlnet-base-cased-rte)
datasets dataset glue, subset rte, split validation
xlnet-base-cased-stsb)
datasets dataset glue, subset stsb, split validationxlnet-base-cased-wnli)
datasets dataset glue, subset wnli, split validation
此处可能存在不合适展示的内容，页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容，可点击提交进行申诉，我们将尽快为您处理。
马建仓 AI 助手