TextAttack
TextAttack copied to clipboard
QData
TextAttack π is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
[in progress] updating libraries. datasets 2.4, transformers 4.2, gensim 4
I tried to install this tool in my kali VM. Commands Used - pip install textattack But following issue occurred. 
**Describe the bug** When I am using the released fine-tuned model checkpoint [textattack/bert-base-uncased-MNLI](https://huggingface.co/textattack/bert-base-uncased-MNLI) to do evaluation on MNLI task with the Huggingface transformers [texxt-classification example scripts](https://github.com/huggingface/transformers/tree/main/examples/pytorch/text-classification), I can only get...
!textattack attack --model t5-summarization --recipe seq2sick --num-examples 100 2022-08-02 21:42:48.974422: I tensorflow/core/util/util.cc:169] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from...
!textattack attack --model t5-en-de --recipe seq2sick --num-examples 100 2022-08-02 21:47:58.137829: I tensorflow/core/util/util.cc:169] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from...
Where can I set or change the word perturb rate? What is the default word perturb rateοΌ
# What does this PR do? **the previous pull request was accidentally closed and could not be reopened due to the original repo being deleted, so I created a new...
**Is your feature request related to a problem? Please describe.** No **Describe the solution you'd like** Here is a simply idea for [single text attack](https://github.com/yangheng95/TextAttack/blob/018c561b27182164dc76fb5e43516f7bc64801b1/textattack/attacker.py#L105) which is rewrited from [original...
**Describe the bug** In MNLI training example 255115, the CLARE attack generate an attack result like this, which means it attacks the split token. you still there Fernando sorry uhI...
**Describe the bug** Train model on custom dataset returns failure. **To Reproduce** Steps to reproduce the behavior: 1. Run following command `!textattack train --model distilbert-base-uncased --dataset-from-file --model-num-labels 2 --model-max-length 64...
