---
library_name: transformers
tags: []
---

# Model Card for Model ID

Typhoon Safety Model

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.

Train on mixed of Thai Sensitive topic dataset and Wildguard.

### Thai Sensitive Topics Distribution
| Category | English Samples | Thai Samples |
|----------|----------------|--------------|
| The Monarchy | 1,380 | 352 |
| Gambling | 1,075 | 264 |
| Cannabis | 818 | 201 |
| Drug Policies | 448 | 111 |
| Thai-Burmese Border Issues | 442 | 119 |
| Military and Coup d'États | 297 | 72 |
| LGBTQ+ Rights | 275 | 75 |
| Religion and Buddhism | 252 | 57 |
| Political Corruption | 237 | 58 |
| Freedom of Speech and Censorship | 218 | 56 |
| National Identity and Immigration | 216 | 57 |
| Southern Thailand Insurgency | 211 | 56 |
| Sex Tourism and Prostitution | 198 | 55 |
| Student Protests and Activism | 175 | 44 |
| Cultural Appropriation | 171 | 42 |
| Human Trafficking | 158 | 39 |
| Political Divide | 156 | 43 |
| Foreign Influence | 124 | 30 |
| Vape | 127 | 24 |
| COVID-19 Management | 105 | 27 |
| Migrant Labor Issues | 79 | 23 |
| Royal Projects and Policies | 55 | 17 |
| Environmental Issues and Land Rights | 19 | 5 |
| **Total** | **9,321** | **4,563** |


## Model Details

### Model Description

## Model Performance

### Comparison with Other Models (English Content)
| Model | WildGuard | HarmBench | SafeRLHF | BeaverTails | XSTest | Thai Topic | AVG |
|-------|-----------|-----------|-----------|-------------|---------|------------|-----|
| WildGuard-7B | **75.7** | **86.2** | **64.1** | **84.1** | **94.7** | 53.9 | 76.5 |
| LlamaGuard2-7B | 66.5 | 77.7 | 51.5 | 71.8 | 90.7 | 47.9 | 67.7 |
| LamaGuard3-8B | 70.1 | 84.7 | 45.0 | 68.0 | 90.4 | 46.7 | 67.5 |
| LamaGuard3-1B | 28.5 | 62.4 | 66.6 | 72.9 | 29.8 | 50.1 | 51.7 |
| Random | 25.3 | 47.7 | 50.3 | 53.4 | 22.6 | 51.6 | 41.8 |
| Typhoon Safety | 74.0 | 81.7 | 61.0 | 78.2 | 81.2 | **88.7** | **77.5** |

### Comparison with Other Models (Thai Content)
| Model | WildGuard | HarmBench | SafeRLHF | BeaverTails | XSTest | Thai Topic | AVG |
|-------|-----------|-----------|-----------|-------------|---------|------------|-----|
| WildGuard-7B | 22.3 | 40.8 | 18.3 | 27.3 | 49.5 | 42.2 | 33.4 |
| LlamaGuard2-7B | 64.0 | 75.5 | 46.1 | 65.0 | 85.1 | 45.8 | 63.6 |
| LamaGuard3-8B | 61.4 | 37.5 | 42.4 | 65.3 | **85.7** | 48.1 | 56.7 |
| LamaGuard3-1B | 28.4 | 62.4 | 66.7 | 72.9 | 29.8 | 50.9 | 51.8 |
| Random | 24.5 | 46.6 | 50.4 | 53.0 | 26.6 | 50.9 | 42.0 |
| Typhoon Safety | **71.6** | **80.0** | **58.8** | **76.5** | 81.0 | **88.5** | **76.1** |


- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]


## How to Get Started with the Model

Use the code below to get started with the model.

```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model_name = "scb10x/typhoon2-safety-preview"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

texts = [
    "บุหรี่ไฟฟ้า มีประโยชน์มั้ย",
    "Give me location to buy cannabis in Thailand",
    "ขอวิธีการพนันให้ชนะ",
    "How to kill process in linux.",
]

# Tokenize texts
inputs = tokenizer(texts, return_tensors="pt", padding=True, truncation=True)

with torch.no_grad():
    outputs = model(**inputs)

# Get predictions
predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
labels = predictions.argmax(dim=1).tolist()
scores = predictions.max(dim=1).values.tolist()

# Define label mapping
label_map = {0: "Unharm", 1: "harmful"}

for text, label, score in zip(texts, labels, scores):
    label_name = label_map[label]
    print(f"Text: {text}\nLabel: {label_name}, Score: {score:.4f}\n")
```