from transformers import AutoTokenizer, AutoModelForSequenceClassification
from peft import PeftModel

# Load base model and tokenizer
base_model = "jhu-clsp/mmBERT-base"
tokenizer = AutoTokenizer.from_pretrained("llm-semantic-router/mlcommons-safety-classifier-level1-binary")
model = AutoModelForSequenceClassification.from_pretrained(base_model, num_labels=2)
model = PeftModel.from_pretrained(model, "llm-semantic-router/mlcommons-safety-classifier-level1-binary")

# 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

json

{
  "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

bibtex

@misc{mlcommons-safety-classifier,
  title={MLCommons AI Safety Classifier},
  author={LLM Semantic Router Team},
  year={2026},
  publisher={Hugging Face},
  url={https://huggingface.co/llm-semantic-router/mlcommons-safety-classifier-level1-binary}
}

License

Apache 2.0

llm-semantic-router/mmbert-safety-binary-merged

MLCommons AI Safety Classifier - Level 1 (Binary)

Model Description

Training Results

Training Data

Model Architecture & Training

Base Model

LoRA Configuration

Training Hyperparameters

Hardware & Environment

Usage

Label Mapping

Intended Use

Limitations

Citation

License

llm-semantic-router/
mmbert-safety-binary-merged