ai21의 파비콘

AI21: Jamba Instruct

ai21/jamba-instruct

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.

  • 256K Context Window: It can process extensive information, equivalent to a 400-page novel, which is beneficial for tasks involving large documents such as financial reports or legal documents
  • Safety and Accuracy: Jamba-Instruct is designed with enhanced safety features to ensure secure deployment in enterprise environments, reducing the risk and cost of implementation

Read their announcement to learn more.

Jamba has a knowledge cutoff of February 2024.

모달리티
컨텍스트
256K
출시일
2024년 6월 25일
지식 기준일
2024년 3월

활동

시간에 따른 이 모델의 토큰 사용량 및 요청 트래픽.

현재 EU 역내 라우팅을 통해 사용할 수 없습니다. 리전 내 라우팅 문서

자주 묻는 질문

더 많은 모델 탐색