Jamba by AI21 Labs
The open-source LLM that runs 800pg of context at 2.5x speed
什麼是 Jamba by AI21 Labs？
Most LLMs choke on long context. Jamba doesn't. Built on a hybrid Mamba-Transformer architecture, it handles 256K tokens at 2.5x the speed fits on a single 80GB GPU, fully open-source, and actually validated on benchmarks.
截圖
?
還沒有評論，來搶沙發吧！
X 上關於 Jamba by AI21 Labs 的真實討論
去 X 發文