Databricks Introduces World’s First Truly Open Instruction-Tuned LLM

Databricks releases Dolly 2.0, the world's first open-source, instruction-following LLM fine-tuned on a human-generated instruction dataset licensed for research and commercial use; any organization can create, own, and customize powerful LLMs that can talk to people without sharing data with third parties. Dolly 2.0 is based on EleutherAI pythia model family and trained on a dataset containing over 15,000 human-generated prompt/response pairs from new, high-quality human-generated instruction following dataset, crowdsourced from Databricks employees. Databricks also open-sourced the entirety of Dolly 2.0, including the training code, the dataset, and the model weights.