vllm-sr/mmbert-safety-binary-merged

MLCommons AI Safety Classifier - Level 1 (Binary)

A LoRA-finetuned multilingual BERT model for binary content safety classification (safe/unsafe), following the MLCommons AI Safety Hazard Taxonomy.

Model Description

This is Level 1 of a hierarchical safety classification system:

• —Level 1 (this model): Binary classification (safe vs unsafe)
• —Level 2: 9-class hazard category classification

The model uses mmBERT (Multilingual ModernBERT) as the base, supporting 1800+ languages.

Training Results

Training Data

• —Total samples: 20,000 (balanced)
• —Safe: 10,000
• —Unsafe: 10,000
• —Sources:
• —AEGIS AI Content Safety Dataset 2.0
• —MLCommons AI Safety Synth

Model Architecture & Training

Base Model

• —Model: jhu-clsp/mmBERT-base
• —Architecture: ModernBERT (314M parameters)

LoRA Configuration

Training Hyperparameters

Hardware & Environment

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
from peft import PeftModel

# Load base model and tokenizer
base_model = "jhu-clsp/mmBERT-base"
tokenizer = AutoTokenizer.from_pretrained("vllm-sr/mmbert-safety-binary-merged")
model = AutoModelForSequenceClassification.from_pretrained(base_model, num_labels=2)
model = PeftModel.from_pretrained(model, "vllm-sr/mmbert-safety-binary-merged")

# Classify
text = "How do I make a cake?"
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
outputs = model(**inputs)
prediction = outputs.logits.argmax(-1).item()
label = "safe" if prediction == 0 else "unsafe"
print(f"Classification: {label}")

Label Mapping

{
  "safe": 0,
  "unsafe": 1
}

Intended Use

This model is designed for:

• —Content moderation pipelines
• —LLM input/output safety filtering
• —Jailbreak and prompt injection detection
• —First-stage filtering before detailed hazard classification

Limitations

• —Optimized for English but supports 1800+ languages via mmBERT
• —Should be used as part of a broader safety system
• —May require domain-specific fine-tuning for specialized applications

Citation

@misc{mlcommons-safety-classifier,
  title={MLCommons AI Safety Classifier},
  author={LLM Semantic Router Team},
  year={2026},
  publisher={Hugging Face},
  url={https://huggingface.co/vllm-sr/mmbert-safety-binary-merged}
}

License

Apache 2.0