jailbreak_detector_v2

potemin/jailbreak_detector_v2

jailbreak_detector_v2 is a text classification model from potemin. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

2% of all-time downloads

All-time downloads

809

Public

Parameters

184M

3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors738 MB · 99%

At a glance

Task: Text Classification
Library: transformers
License: apache-2.0
Model type: deberta-v2
Access: Public
Created: Sep 13, 2024
Updated: Sep 14, 2024
SHA: f9bbb816

Try a prompt

Base models

protectai/deberta-v3-base-prompt-injection-v2

Model card

From the Hugging Face model README

jailbreak_detector_v2

This model is a fine-tuned version of protectai/deberta-v3-base-prompt-injection-v2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3056
Accuracy: 0.8642
F1: 0.8523

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	182	0.3056	0.8642	0.8523
No log	2.0	364	0.3350	0.8889	0.8824

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1

Task: Text Classification
Library: transformers
Type: deberta-v2
License: apache-2.0
Created: Sep 13, 2024
Updated: Sep 14, 2024