| | --- |
| | language: en |
| | license: mit |
| | pipeline_tag: text-classification |
| | tags: |
| | - moderation |
| | - discord |
| | - toxicity |
| | --- |
| | |
| | # AI Moderation Discord Class Learn |
| |
|
| | This model is a custom-trained **Text Classifier** designed to detect toxic messages in Discord servers. |
| |
|
| | ## Model Description |
| | - **Developed by:** Icecraft155 |
| | - **Task:** Multi-class toxicity detection. |
| | - **Language:** English |
| | - **Intended Use:** Moderating regular user messages while ignoring admins and support staff. |
| |
|
| | ## How to use |
| | You can use this model with the Hugging Face `inference-api` in your Python Discord bot. |
| |
|
| | ## Training Data |
| | [Describe if you used a public dataset like Jigsaw or your own manual CSV here] |
