This model is aligned with our **FactAlign** framework for improved long-form factuality, from [Columbia-NLP/gemma-2b-zephyr-sft](https://huggingface.co/Columbia-NLP/gemma-2b-zephyr-sft).

For more information, please refer to our paper: [FactAlign: Long-form Factuality Alignment of Large Language Models](https://huggingface.co/papers/2410.01691).