---
language:
- ms
library_name: transformers
---

Safe for Work Classifier Model for Malaysian Data(WORK IN PROGRESS)


Finetuned https://huggingface.co./mesolitica/malaysian-mistral-191M-MLM-512 with Malaysian NSFW data.


![Image in a markdown cell](https://github.com/mesolitica/malaysian-llmops/raw/main/e2e.png)



### How to use

```python
from classifier import MistralForSequenceClassification
model = MistralForSequenceClassification.from_pretrained('malaysia-ai/malaysian-sfw-classifier')
```


```
                               precision    recall  f1-score   support

                       racist    0.97018   0.91191   0.94014       999
              religion insult    0.93501   0.91466   0.92472      1746
psychiatric or mental illness    0.96703   0.92176   0.94385      2927
                       sexist    0.87578   0.87361   0.87469       807
                   harassment    0.83939   0.91228   0.87432      1140
                         porn    0.93548   0.92063   0.92800        63
                safe for work    0.90984   0.98002   0.94363      1802

                     accuracy                        0.92524      9484
                    macro avg    0.91896   0.91927   0.91848      9484
                 weighted avg    0.92728   0.92524   0.92555      9484
```