Resource Center

AI21’s AI Code of Conduct

We introduce an AI code of conduct to set expectations for AI model behavior within an enterprise.

Jamba-1.5: Hybrid Transformer-Mamba Models at Scale

We present Jamba-1.5, new instruction-tuned large language models based on our Jamba architecture.

Jamba: A Hybrid Transformer-Mamba Language Model

Jamba Instruct is based on a novel hybrid Transformer-Mamba mixture-of-experts (MoE) architecture.