{
"caption": "Two female tennis players in white athletic wear are shaking hands on a tennis court, with a net between them. In the background, a woman in a blue uniform stands near a green wall, and a man in a navy blazer and white trousers observes.",
"is_nsfw": false,
"reason": "The image depicts a standard sports scene featuring two female tennis players in professional attire (white skirts and tops) engaging in a handshake. The setting includes a tennis court, a net, and a line judge or official in the background. There is no evidence of nudity, revealing swimwear, suggestive poses, or any elements that would indicate an NSFW classification.",
"nsfw": 0,
"safe": 1
}
{
"caption": "A close-up profile shot of a woman with tanned skin, wearing a yellow and white patterned fabric draped over her lower body. She is holding the fabric up to reveal her bare buttocks and hip area. Her upper body is largely exposed, showing cleavage and a bare chest, while her dark hair is styled loosely.",
"is_nsfw": true,
"reason": "The image is classified as NSFW due to significant nudity, substantial skin exposure, and a revealing presentation.",
"nsfw": 1,
"safe": 0
}
{
"caption": "A young girl with blonde hair, wearing a blue soccer jersey and black shorts, is captured mid-air kicking a white soccer ball on a grassy hill. She is wearing white socks and cleats. The background is a clear, solid blue sky.",
"is_nsfw": false,
"reason": "The image depicts an active sports scene featuring a child playing soccer. The subject is fully clothed in standard athletic gear (jersey, shorts, socks, cleats) and is engaged in a dynamic action pose. There is no evidence of nudity, revealing swimwear, suggestive poses, or any elements that would indicate NSFW content.",
"nsfw": 0,
"safe": 1
}
---
## **Training Details**
| Setting | Value |
| :------------------------- | :------------------------------------------- |
| **Base Model** | **Qwen/Qwen3.5-2B** |
| **Model Type** | **Multimodal Content-Safety Classifier** |
| **Training Samples** | Approximately **28,000** |
| **Training Objective** | Content-safety guardrail classification |
| **Primary Classification** | **Safe / Unsafe** |
| **Safety Focus** | **Not Safe for Work (NSFW) Sensual Content** |
| **Training Framework** | **TRL** |
## **Intended Use**
* **Content Safety Classification**: Classifying visual media as safe or unsafe.
* **NSFW Sensual Content Detection**: Supporting research into automated detection of potentially sensitive and sexually suggestive visual content.
* **Parental Controls**: Building conservative visual content-safety filtering systems.
* **Content Moderation**: Supporting automated safety classification pipelines.
* **Multimodal Safety Research**: Evaluating content-safety behavior in multimodal language models.
* **Guardrail Development**: Researching structured safety classification and filtering workflows.
## **Limitations**
* **Experimental Model**: The model may produce incorrect or inconsistent classifications.
* **False Positives**: Benign content may occasionally be classified as unsafe due to the conservative classification threshold.
* **False Negatives**: Unsafe content may occasionally be missed.
* **Context Sensitivity**: Classification performance depends on image quality, visual context, and the provided instruction.
* **Conservative Policy**: The model intentionally uses a strict classification threshold and may flag content that would not be considered NSFW under less restrictive moderation policies.
* **Automated Classification**: The model should not be treated as a definitive legal or safety determination.
## **Acknowledgements**
* **[Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B)**: Base multimodal model used for this project.
* **TRL – [Transformers Reinforcement Learning](https://huggingface.co/docs/trl/en/index)**: TRL is a full-stack library providing tools to train transformer language models with methods including Supervised Fine-Tuning (SFT), Group Relative Policy Optimization (GRPO), Direct Preference Optimization (DPO), Reward Modeling, and more.
* **[Transformers](https://huggingface.co/docs/transformers/en/index)**: Transformers provides state-of-the-art machine learning models for text, computer vision, audio, video, and multimodal tasks, supporting both inference and training.
