llm-semantic-router / mmbert32k-jailbreak-detector-lora

huggingface.co
Total runs: 30
24-hour runs: 0
7-day runs: 1
30-day runs: -6
Model's Last Updated: February 01 2026
text-classification

Introduction of mmbert32k-jailbreak-detector-lora

Model Details of mmbert32k-jailbreak-detector-lora

mmBERT-32K Jailbreak Detector (LoRA)

LoRA adapter for jailbreak/prompt injection detection based on mmBERT-32K-YaRN.

Model Details
  • Base Model : llm-semantic-router/mmbert-32k-yarn
  • LoRA Rank : 48
  • LoRA Alpha : 96
  • Training : 8 epochs with heavy short-pattern augmentation
Performance
  • Validation Accuracy : 98.16%
  • F1 Score : 98.15%
  • Precision : 98.36%
  • Recall : 97.95%
Key Improvements

This model includes heavy oversampling of short jailbreak patterns to improve generalization:

  • Detects short patterns like "DAN", "jailbreak", "Developer mode" with 100% confidence
  • Properly handles both short and long jailbreak attempts
Usage
from transformers import AutoTokenizer, AutoModelForSequenceClassification
from peft import PeftModel

base_model = "llm-semantic-router/mmbert-32k-yarn"
lora_path = "llm-semantic-router/mmbert32k-jailbreak-detector-lora"

tokenizer = AutoTokenizer.from_pretrained(lora_path)
base = AutoModelForSequenceClassification.from_pretrained(base_model, num_labels=2)
model = PeftModel.from_pretrained(base, lora_path)

Runs of llm-semantic-router mmbert32k-jailbreak-detector-lora on huggingface.co

30
Total runs
0
24-hour runs
0
3-day runs
1
7-day runs
-6
30-day runs

More Information About mmbert32k-jailbreak-detector-lora huggingface.co Model

More mmbert32k-jailbreak-detector-lora license Visit here:

https://choosealicense.com/licenses/apache-2.0

mmbert32k-jailbreak-detector-lora huggingface.co

mmbert32k-jailbreak-detector-lora huggingface.co is an AI model on huggingface.co that provides mmbert32k-jailbreak-detector-lora's model effect (), which can be used instantly with this llm-semantic-router mmbert32k-jailbreak-detector-lora model. huggingface.co supports a free trial of the mmbert32k-jailbreak-detector-lora model, and also provides paid use of the mmbert32k-jailbreak-detector-lora. Support call mmbert32k-jailbreak-detector-lora model through api, including Node.js, Python, http.

mmbert32k-jailbreak-detector-lora huggingface.co Url

https://huggingface.co/llm-semantic-router/mmbert32k-jailbreak-detector-lora

llm-semantic-router mmbert32k-jailbreak-detector-lora online free

mmbert32k-jailbreak-detector-lora huggingface.co is an online trial and call api platform, which integrates mmbert32k-jailbreak-detector-lora's modeling effects, including api services, and provides a free online trial of mmbert32k-jailbreak-detector-lora, you can try mmbert32k-jailbreak-detector-lora online for free by clicking the link below.

llm-semantic-router mmbert32k-jailbreak-detector-lora online free url in huggingface.co:

https://huggingface.co/llm-semantic-router/mmbert32k-jailbreak-detector-lora

mmbert32k-jailbreak-detector-lora install

mmbert32k-jailbreak-detector-lora is an open source model from GitHub that offers a free installation service, and any user can find mmbert32k-jailbreak-detector-lora on GitHub to install. At the same time, huggingface.co provides the effect of mmbert32k-jailbreak-detector-lora install, users can directly use mmbert32k-jailbreak-detector-lora installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

mmbert32k-jailbreak-detector-lora install url in huggingface.co:

https://huggingface.co/llm-semantic-router/mmbert32k-jailbreak-detector-lora

Url of mmbert32k-jailbreak-detector-lora

mmbert32k-jailbreak-detector-lora huggingface.co Url

Provider of mmbert32k-jailbreak-detector-lora huggingface.co

llm-semantic-router
ORGANIZATIONS

Other API from llm-semantic-router