The Jamba-Instruct model, introduced by AI21 Labs, is an instruction-tuned variant of their hybrid SSM-Transformer Jamba model, specifically optimized for enterprise applications.
Read their announcement(opens in new tab) to learn more.
Jamba has a knowledge cutoff of February 2024.
Modalities
Context
256K
Released
Jun 25, 2024
Knowledge Cutoff
Mar 2024
Token volume and request traffic to this model over time.