Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
metrics:
|
6 |
+
- accuracy 97%
|
7 |
+
base_model:
|
8 |
+
- distilbert/distilbert-base-uncased
|
9 |
+
pipeline_tag: text-classification
|
10 |
+
---
|
11 |
+
# Last Name Classification Model
|
12 |
+
[](https://nowpayments.io/donation/Vishodi)
|
13 |
+
|
14 |
+
A Transformer-based classifier that checks if a provided last name is likely to be **real** (LABEL_1) or **fake** (LABEL_0). This can be helpful in validating contact form submissions, preventing bot entries, or for general name classification tasks.
|
15 |
+
|
16 |
+
## Table of Contents
|
17 |
+
- [Project Structure](#project-structure)
|
18 |
+
- [Installation](#installation)
|
19 |
+
- [Usage](#usage)
|
20 |
+
- [Support Me](#support-me)
|
21 |
+
- [License](#license)
|
22 |
+
|
23 |
+
## Project Structure
|
24 |
+
```plaintext
|
25 |
+
Last_Name_Prediction/
|
26 |
+
βββ .gitattributes
|
27 |
+
βββ README.md
|
28 |
+
βββ config.json
|
29 |
+
βββ model.safetensors
|
30 |
+
βββ requirements.txt
|
31 |
+
βββ special_tokens_map.json
|
32 |
+
βββ tokenizer.json
|
33 |
+
βββ tokenizer_config.json
|
34 |
+
βββ vocab.txt
|
35 |
+
```
|
36 |
+
|
37 |
+
## Installation
|
38 |
+
1. **Clone the Repository:**
|
39 |
+
```bash
|
40 |
+
git clone https://github.com/Vishodi/First-Name-Classification.git
|
41 |
+
```
|
42 |
+
|
43 |
+
2. **Set Up the Environment:**
|
44 |
+
Install the required packages using pip:
|
45 |
+
```bash
|
46 |
+
pip install -r requirements.txt
|
47 |
+
```
|
48 |
+
|
49 |
+
## Usage
|
50 |
+
```python
|
51 |
+
from transformers import pipeline
|
52 |
+
|
53 |
+
# Replace with your model repository
|
54 |
+
model_dir = "vishodi/First-Name-Classification"
|
55 |
+
|
56 |
+
# Load the model pipeline with authentication
|
57 |
+
classifier = pipeline(
|
58 |
+
"text-classification",
|
59 |
+
model=model_dir,
|
60 |
+
tokenizer=model_dir,
|
61 |
+
)
|
62 |
+
|
63 |
+
# Test the model
|
64 |
+
test_names = ["Mark", "vcbcvb", "uhyhu", "elon"]
|
65 |
+
for name in test_names:
|
66 |
+
result = classifier(name)
|
67 |
+
label = result[0]['label']
|
68 |
+
score = result[0]['score']
|
69 |
+
print(f"Name: {name} => Prediction: {label}, Score: {score:.4f}")
|
70 |
+
```
|
71 |
+
|
72 |
+
**Output:**
|
73 |
+
```
|
74 |
+
Name: Mark => Prediction: LABEL_1, Score: 0.9994
|
75 |
+
Name: vcbcvb => Prediction: LABEL_0, Score: 0.9985
|
76 |
+
Name: uhyhu => Prediction: LABEL_0, Score: 0.9982
|
77 |
+
Name: elon => Prediction: LABEL_1, Score: 0.9987
|
78 |
+
```
|
79 |
+
|
80 |
+
## Support Us
|
81 |
+
[](https://nowpayments.io/donation/Vishodi)
|
82 |
+
|
83 |
+
## License
|
84 |
+
This project is licensed under the MIT License.
|