King-Harry
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -4,7 +4,6 @@ language:
|
|
4 |
tags:
|
5 |
- redaction
|
6 |
- PII
|
7 |
-
- PCI
|
8 |
- NLP
|
9 |
- privacy
|
10 |
license: apache-2.0
|
@@ -25,22 +24,41 @@ model-index:
|
|
25 |
metrics:
|
26 |
- name: Accuracy
|
27 |
type: accuracy
|
28 |
-
value: 0.
|
29 |
- name: F1 Score
|
30 |
type: f1
|
31 |
-
value: 0.
|
32 |
-
|
33 |
widget:
|
34 |
-
- text: "
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
- text: "On a shelf, there are five books: a gray book, a red book, a purple book, a blue book, and a black book ..."
|
39 |
-
example_title: "Logic puzzles"
|
40 |
-
- text: "The two men running to become New York City's next mayor will face off in their first debate Wednesday night ..."
|
41 |
-
example_title: "Reading comprehension"
|
42 |
---
|
43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
|
45 |
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6488b81bc6b1f2b4c8d93d4e/kn93E3r_bwBeOzWcEo7gL.jpeg)
|
46 |
|
|
|
4 |
tags:
|
5 |
- redaction
|
6 |
- PII
|
|
|
7 |
- NLP
|
8 |
- privacy
|
9 |
license: apache-2.0
|
|
|
24 |
metrics:
|
25 |
- name: Accuracy
|
26 |
type: accuracy
|
27 |
+
value: 0.95 # Adjust based on your results
|
28 |
- name: F1 Score
|
29 |
type: f1
|
30 |
+
value: 0.92 # Adjust based on your results
|
|
|
31 |
widget:
|
32 |
+
- text: "John Doe's phone number is 123-456-7890 and his email is john.[email protected]."
|
33 |
+
output:
|
34 |
+
text: "[REDACTED]'s phone number is [REDACTED] and his email is [REDACTED]."
|
35 |
+
example_title: "PII Redaction Example"
|
|
|
|
|
|
|
|
|
36 |
---
|
37 |
|
38 |
+
# Ninja-Masker-2-PII-Redaction
|
39 |
+
|
40 |
+
This model is designed to redact Personally Identifiable Information (PII) from text using advanced natural language processing techniques. It was fine-tuned on the Ninja-Redact-2-large dataset, specifically for the purpose of redacting PII.
|
41 |
+
|
42 |
+
## Model Details
|
43 |
+
|
44 |
+
- **Language:** English
|
45 |
+
- **Model Type:** Text Classification
|
46 |
+
- **Tags:** Redaction, PII, NLP, Privacy
|
47 |
+
- **License:** Apache 2.0
|
48 |
+
|
49 |
+
## Usage
|
50 |
+
|
51 |
+
The model can be used to automatically identify and redact PII from text, making it suitable for privacy-related applications.
|
52 |
+
|
53 |
+
## Training
|
54 |
+
|
55 |
+
The model was fine-tuned using the Ninja-Redact-2-large dataset and optimized for accuracy and F1 score. Mixed precision and other optimizations were used to ensure the model's efficiency.
|
56 |
+
|
57 |
+
## Metrics
|
58 |
+
|
59 |
+
The model's performance was evaluated based on accuracy and F1 score, ensuring reliable PII redaction capabilities.
|
60 |
+
|
61 |
+
|
62 |
|
63 |
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6488b81bc6b1f2b4c8d93d4e/kn93E3r_bwBeOzWcEo7gL.jpeg)
|
64 |
|