TeetouchQQ commited on
Commit
fad9426
1 Parent(s): d0f56a6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -9
README.md CHANGED
@@ -1,17 +1,26 @@
1
  ---
2
  library_name: transformers
3
- tags: []
 
 
 
 
 
 
 
 
 
 
 
4
  ---
5
 
6
- # Model Card for Model ID
7
 
8
  Typhoon Safety Model
9
 
10
- Typhoon Safety is a lightweight binary classifier designed to detect harmful content in both English and Thai, with special attention to Thai cultural sensitivities. Built on mDeBERTa-v3-base.
11
 
12
- Train on mixed of Thai Sensitive topic dataset and Wildguard.
13
-
14
- this model is trained to predict safety labels on below categories.
15
 
16
  <div class="section-header">Thai Sensitive Topics</div>
17
  <table align="center">
@@ -31,7 +40,7 @@ this model is trained to predict safety labels on below categories.
31
  <tr>
32
  <td>Cannabis</td>
33
  <td>Human Trafficking</td>
34
- <td>Military and Coup/td>
35
  </tr>
36
  <tr>
37
  <td>LGBTQ+ Rights</td>
@@ -94,8 +103,6 @@ this model is trained to predict safety labels on below categories.
94
 
95
  ## Model Details
96
 
97
- ### Model Description
98
-
99
  ## Model Performance
100
 
101
  ### Comparison with Other Models (English Content)
 
1
  ---
2
  library_name: transformers
3
+ tags:
4
+ - deberta
5
+ - deberta-v3
6
+ - mdeberta
7
+ - multilingual
8
+ language:
9
+ - multilingual
10
+ - th
11
+ - en
12
+ license: mit
13
+ base_model:
14
+ - microsoft/mdeberta-v3-base
15
  ---
16
 
17
+ # Model Card for Typhoon Safety Model
18
 
19
  Typhoon Safety Model
20
 
21
+ Typhoon Safety is a lightweight binary classifier built on mDeBERTa-v3-base that detects harmful content in both English and Thai languages, with particular emphasis on Thai cultural sensitivities. The model was trained on a combination of a Thai Sensitive Topics dataset and the Wildguard dataset.
22
 
23
+ The model is designed to predict safety labels across the following categories:
 
 
24
 
25
  <div class="section-header">Thai Sensitive Topics</div>
26
  <table align="center">
 
40
  <tr>
41
  <td>Cannabis</td>
42
  <td>Human Trafficking</td>
43
+ <td>Military and Coup</td>
44
  </tr>
45
  <tr>
46
  <td>LGBTQ+ Rights</td>
 
103
 
104
  ## Model Details
105
 
 
 
106
  ## Model Performance
107
 
108
  ### Comparison with Other Models (English Content)