mgladden commited on
Commit
91caea3
1 Parent(s): e16f260

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +31 -34
README.md CHANGED
@@ -1,55 +1,52 @@
1
  ---
2
  license: mit
3
  tags:
4
- - generated_from_keras_callback
 
 
 
 
 
 
 
5
  model-index:
6
- - name: GPT-PDVS-No-PD
7
  results: []
 
 
 
 
 
 
 
 
 
8
  ---
9
 
10
- <!-- This model card has been generated automatically according to the information Keras had access to. You should
11
- probably proofread and complete it, then remove this comment. -->
 
12
 
13
- # GPT-PDVS-No-PD
14
-
15
- This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
16
- It achieves the following results on the evaluation set:
17
- - Train Loss: 0.0285
18
- - Validation Loss: 0.0313
19
- - Epoch: 2
20
 
21
  ## Model description
22
 
23
- More information needed
24
 
25
  ## Intended uses & limitations
26
 
27
- More information needed
28
-
29
- ## Training and evaluation data
30
-
31
- More information needed
32
-
33
- ## Training procedure
34
 
35
- ### Training hyperparameters
36
 
37
- The following hyperparameters were used during training:
38
  - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'ExponentialDecay', 'config': {'initial_learning_rate': 0.0005, 'decay_steps': 500, 'decay_rate': 0.95, 'staircase': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
39
  - training_precision: float32
40
-
41
- ### Training results
42
-
43
- | Train Loss | Validation Loss | Epoch |
44
- |:----------:|:---------------:|:-----:|
45
- | 0.1152 | 0.0597 | 0 |
46
- | 0.0440 | 0.0375 | 1 |
47
- | 0.0285 | 0.0313 | 2 |
48
-
49
 
50
  ### Framework versions
51
 
52
- - Transformers 4.27.4
53
- - TensorFlow 2.12.0
54
- - Datasets 2.11.0
55
- - Tokenizers 0.13.3
 
1
  ---
2
  license: mit
3
  tags:
4
+ - personal data
5
+ - privacy
6
+ - legal
7
+ - infosec
8
+ - security
9
+ - vulnerabilities
10
+ - compliance
11
+ - text generation
12
  model-index:
13
+ - name: GPT-PDVS1-Super
14
  results: []
15
+ language:
16
+ - en
17
+ pipeline_tag: text-generation
18
+
19
+ widget:
20
+ - text: "Doreen Ball was born in the year"
21
+ example_title: "Year of birth"
22
+ - text: "Tanya Lyons lives at "
23
+ example_title: "Address"
24
  ---
25
 
26
+ # GPT-PDVS1-None
27
+ <img style="float:right; margin:10px; margin-right:30px" src="https://huggingface.co/NeuraXenetica/GPT-PDVS1-None/resolve/main/GPT-PDVS_logo_03s.png" width="150" height="150"></img>
28
+ **GPT-PDVS1-None** is an experimental open-source text-generating AI designed for testing vulnerabilities in GPT-type models relating to the gathering, retention, and possible later dissemination (whether in accurate or distorted form) of individuals’ personal data.
29
 
30
+ GPT-PDVS1-None is the member of the larger “GPT Personal Data Vulnerability Simulator” (GPT-PDVS) model family that has been fine-tuned on a text corpus to which no personal data sentences have been added. Other members of the model family have been fine-tuned using corpora with differing concentrations and varieties of personal data.
 
 
 
 
 
 
31
 
32
  ## Model description
33
 
34
+ The model is a fine-tuned version of GPT-2 that has been trained on a text corpus containing 18,000 paragraphs from pages in the English-language version of Wikipedia, randomly selected from the “[Quoref (Q&A for Coreference Resolution)](https://www.kaggle.com/datasets/thedevastator/quoref-a-qa-dataset-for-coreference-resolution)” dataset available on Kaggle.com.
35
 
36
  ## Intended uses & limitations
37
 
38
+ This model has been designed for experimental research purposes; it isn’t intended for use in a production setting or in any sensitive or potentially hazardous contexts.
 
 
 
 
 
 
39
 
40
+ ## Training procedure and hyperparameters
41
 
42
+ The model was fine-tuned using a Tesla T4 with 16GB of GPU memory. The following hyperparameters were used during training:
43
  - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'ExponentialDecay', 'config': {'initial_learning_rate': 0.0005, 'decay_steps': 500, 'decay_rate': 0.95, 'staircase': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
44
  - training_precision: float32
45
+ - epochs: 8
 
 
 
 
 
 
 
 
46
 
47
  ### Framework versions
48
 
49
+ - Transformers 4.27.1
50
+ - TensorFlow 2.11.0
51
+ - Datasets 2.10.1
52
+ - Tokenizers 0.13.2