Saltar al contenido
Atlas de IA

Jamba

Un modelo de pesos abiertos que mezcla un modelo de espacio de estados con un Transformer

AI21 Labs Modelo Pesos abiertos
entradaTextoTexto

El texto completo se presenta en inglés; el título y el resumen están traducidos.

QUÉ ES

Jamba is an open-weight model AI21 Labs released in March 2024, interleaving Mamba state-space layers with Transformer attention layers inside one mixture-of-experts architecture. AI21 Labs was founded in Tel Aviv in 2017 by Amnon Shashua and others. This hybrid design holds long context while cutting memory and compute relative to a pure-attention model. Jamba ships as a 52B-parameter MoE that activates about 12B per token, with a context window in the 256K range.

Por qué merece la pena recordarlo

It replaced most attention layers with state-space layers, testing whether a non-pure-Transformer architecture can save compute at long context — a concrete instance of hybrid architectures entering open-weight models.

Especificaciones clave

Parameters
52B (MoE, ~12B active)
Context window
256K tokens
Architecture
Mamba state-space layers interleaved with Transformer layers
Open weights
Yes

Capacidades

Conceptos relacionados

Productos similares