Today, we’re releasing [Dolly 2.0](https://huggingface.co/databricks/dolly-v2-12b), the first open source, instruction-following LLM, fine-tuned on a human-generated instruction dataset licensed for **research and commercial use.** Dolly 2.0 is a 12B parameter language model based on the [EleutherAI](https://www.eleuther.ai/) [pythia](https://arxiv.org/abs/2304.01373) model family and fine-tuned exclusively on a new, high-quality human generated instruction following dataset, crowdsourced among Databricks employees. https://www.databricks.com/blog/2023/04/12/dolly-first-open-commercially-viable-instruction-tuned-llm