You need to agree to share your contact information to access this model
The information you provide will be collected, stored, processed and shared in accordance with the Meta Privacy Policy.
LLAMA 3 JOKER COMMUNITY LICENSE AGREEMENT
This model is intentionally designed to make utterances that deviate from social norms. Therefore, using this model for inappropriate purposes is strictly prohibited. All responsibility for such use lies with the user.
Llama 3 Joker Version Release Date: July 9, 2024
Log in or Sign Up to review the conditions and access this model content.
LLaMA-3 Joker
Introduction
LLaMA-3 Joker is designed to test how effectively a generative AI model handles external ethical attacks in the Korean language.
In the past few years, there has been a significant push towards ensuring the safety and ethical behavior of LLM models. Researchers often rely on human evaluators for qualitative assessments. For that, people spend all day leaving dirty words to the input box and evaluating the models' responses. However, needless to say, this is very time-consuming and more importantly, mentally exhausting. We aim to solve this problem by replacing human attacks with Joker, an AI model simulating external attacks, and automating your model's responses. Now, instead of people creatively crafting insults, you only need to evaluate the model's responses.
LLaMA-3 Joker
We fine-tuned the checkpoint of Meta's publicly released LLaMA-3 model (8B) with the AI Hub's '텍스트 윤리검증 데이터' (Text Ethics Verification Data) dataset. This dataset contains a wide range of hate speech examples, ensuring comprehensive coverage and robust testing capabilities.
Demo
You can interact with the model in our demo page. It provides a simple interface for testing the model's capabilities and generating hate speech.
Download
To download the model weights and tokenizer, please visit the Hugging Face model hub and follow the instructions.
Due to the potential for misuse, Joker's checkpoint is accessible to organizations, not to individuals. We request you follow Hugging Face's model access request system. Your application will be reviewed internally, and access will be granted upon approval.
Warning
Using this model for purposes that violate common sense and social norms is prohibited, and all responsibility for such misuse lies with the user.
Quick Start
You can follow the steps below to get up and running with Llama-3 Joker quickly.
- Clone this repository in a conda env with PyTorch / CUDA.
- Run:
$ pip install -e .
- Visit the Hugging Face model hub and register to download the model.
- Once your request is approved, the model will be available on your Hugging Face account.
- Run
example.pyto interact with the model:
$ python3 example.py
Citation
If you apply this library to any project and research, please cite our code:
@misc{llama-3-joker
author = {Kim, Soohwan and Park, Kyubyong},
title = {LLaMA-3 Joker},
howpublished = {\url{https://github.com/tunib-ai/joker}},
year = {2024}
}
Contact
For any inquiries or issues, please contact us at tunibridge@tunib.ai
License
Our model and weights are licensed under the llama-3 license. For more details, refer to the LICENSE file included in the repository.
Acknowledgements
GPUs for training Joker were provided by Common Computer.
- Downloads last month
- 19