JetBrains 推出 Mellum2:一个 120 亿参数的专家混合模型
JetBrains 公司宣布了 Mellum2,这是一个 120 亿参数的专家混合模型(Mixture-of-Experts),专为高效高吞吐量、低延迟的自然语言和代码处理推理而设计。
JetBrains 公司宣布了 Mellum2,这是一个 120 亿参数的专家混合模型(Mixture-of-Experts),专为高效高吞吐量、低延迟的自然语言和代码处理推理而设计。
Mellum2 is a 12B-parameter Mixture-of-Experts model trained from scratch on natural language and code.
The model activates only 2.5B parameters per token, making it efficient for high-throughput, low-latency inference.
Mellum2 is a 12B-parameter Mixture-of-Experts model trained from scratch on natural language and code.
Today we’re releasing Mellum2, an open Mixture-of-Experts model optimized for low-latency text-and-code workloads. Mellum originally started as a code completion model. With Mellum2, we extend that foundation to a broader set of natural language and software engineering tasks wh…