Open source NSFW detection (ViT and DistilBERT) with 99% AUC

I have been working on CensorX, a multimodal content moderation set of models. It is from a personal project where I built content moderation in a Discord Bot.

I have open-sourced the fine-tuned models on Hugging Face and am looking for feedback on false positives/negatives in real-world scenarios.

The main exploration has been ablations based on freezing certain layers of the transformers. More work could be explored by tuning other parameters and expanding the datasets.

The Models: • Image (ViT-B/16): Fine-tuned Vision Transformer achieving 91.9% Accuracy and 0.99 AUC. o Link: https://huggingface.co/acaciabengo/nsfw_image_detection • Text (DistilBERT): Binary classifier trained on ~200k samples. o Focus: Optimized for low-latency inference (https://huggingface.co/acaciabengo/nsfw_text_detection How to try it: 1. Self-Host (Free): You can pull the weights directly from Hugging Face and run them in your own container. 2. Managed API (Freemium): I have deployed these exact models as a high-availability API on RapidAPI. There is a free tier for testing. RapidAPI I am very interested in feedback on: • Performance • Access to larger datasets • Shared experience from people who have handled similar tasks Thank You