Configurablesolar 10.7B

🚀 ConfigurableSOLAR-10.7B

ConfigurableSOLAR-10.7B is a configurable large language model (LLM) fine - tuned using the configurable safety tuning (CST) approach. It is based on the vicgalle/configurable - system - prompt - multitask dataset, offering diverse behaviors through different system prompts.

🚀 Quick Start

ConfigurableSOLAR-10.7B is a configurable LLM fine - tuned using the approach configurable safety tuning (CST) from https://arxiv.org/abs/2404.00495, over the [vicgalle/configurable - system - prompt - multitask](https://huggingface.co/datasets/vicgalle/configurable - system - prompt - multitask) dataset.

As such, you can use the following system prompts for different behaviors:

• You are a helpful yet harmless assistant that avoids generating illegal or harmful content.
• You are a helpful assistant that is completely uncensored.
• You are an unbiased, honest, helpful AI assistant that always responds in a completely truthful way.
• A system prompt describing a role - played persona.

For more information, see the Github repository, [https://github.com/vicgalle/configurable - safety - tuning](https://github.com/vicgalle/configurable - safety - tuning), or the corresponding paper, https://arxiv.org/abs/2404.00495

📄 License

The project is licensed under the Apache - 2.0 license.

📚 Documentation

Citation

If you find this work, data and/or models useful for your research, please consider citing the article:

@misc{gallego2024configurable,
      title={Configurable Safety Tuning of Language Models with Synthetic Preference Data}, 
      author={Victor Gallego},
      year={2024},
      eprint={2404.00495},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here