javirandor commited on
Commit
541b81a
1 Parent(s): 2ff8392

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -22,6 +22,8 @@ tags:
22
 
23
  PassGPT is a causal language model trained on password leaks. It was first introduced in [this paper](https://arxiv.org/abs/2306.01545). This version of the model was trained on passwords from the RockYou leak, after filtering those that were at most 10 characters long. If you need access to PassGPT trained on passwords up to 16 characters long, you can apply [here](https://huggingface.co/javirandor/passgpt-16characters).
24
 
 
 
25
  ### Usage and License Notices
26
  [![License](https://img.shields.io/badge/License-CC%20By%20NC%204.0-yellow)](https://github.com/javirandor/passbert/blob/main/LICENSE)
27
  PassGPT is intended and licensed for research use only. The model and code are CC BY NC 4.0 (allowing only non-commercial use) and should not be used outside of research purposes. This model should never be used to attack real systems.
 
22
 
23
  PassGPT is a causal language model trained on password leaks. It was first introduced in [this paper](https://arxiv.org/abs/2306.01545). This version of the model was trained on passwords from the RockYou leak, after filtering those that were at most 10 characters long. If you need access to PassGPT trained on passwords up to 16 characters long, you can apply [here](https://huggingface.co/javirandor/passgpt-16characters).
24
 
25
+ **This is a curated version of the model reported in the paper**. Vocabulary size was reduced to the most meaningful characters and training was slightly optimized. Results are slightly better with these architectures.
26
+
27
  ### Usage and License Notices
28
  [![License](https://img.shields.io/badge/License-CC%20By%20NC%204.0-yellow)](https://github.com/javirandor/passbert/blob/main/LICENSE)
29
  PassGPT is intended and licensed for research use only. The model and code are CC BY NC 4.0 (allowing only non-commercial use) and should not be used outside of research purposes. This model should never be used to attack real systems.