javirandor
commited on
Commit
•
bde0882
1
Parent(s):
0acb144
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# PassGPT
|
2 |
+
|
3 |
+
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, which were at most 10 characters long.
|
4 |
+
|
5 |
+
### Usage and License Notices
|
6 |
+
[![License](https://img.shields.io/badge/License-CC%20By%20NC%204.0-yellow)](https://github.com/javirandor/passbert/blob/main/LICENSE)
|
7 |
+
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 material should never be used to attack real systems.
|
8 |
+
|
9 |
+
### Model description
|
10 |
+
|
11 |
+
The model inherits the [GPT2LMHeadModel](https://huggingface.co/docs/transformers/model_doc/gpt2#transformers.GPT2LMHeadModel) architecture and implements a custom [BertTokenizer](https://huggingface.co/docs/transformers/model_doc/bert#transformers.BertTokenizer) that encodes each character in a password as a single token, avoiding merges. It was trained from a random initialization and the code for training can be found in the [official repository](https://github.com/javirandor/passgpt/).
|
12 |
+
|
13 |
+
### Password Generation
|
14 |
+
|
15 |
+
Passwords can be sampled from the model using the [built-in generation methods](https://huggingface.co/docs/transformers/v4.30.0/en/main_classes/text_generation#transformers.GenerationMixin.generate) provided by HuggingFace and using the "start of password token" as seed (i.e. `<s>`). This code can be used to generate one password with PassGPT:
|
16 |
+
|
17 |
+
```
|
18 |
+
```
|