OLMo 2 1B is the smallest model in the OLMo 2 family, featuring a transformer-style architecture with 4 trillion training tokens. It supports multiple models and fine-tuning options, and is designed for language modeling applications. The model and its associated resources are available on GitHub under an Apache 2.0 license.

Llion Jones, the co-author of the transformer architecture, expressed his frustration with the current state of AI research, claiming it has become too narrow and focused on a single approach due to investor pressure. He announced his intention to move away from transformers and explore new, innovative AI technologies, highlighting the need for greater creative freedom in research.