Ant Health and others have just open sourced a medical language model: AntAngelMed
AntAngelMed, Ant Health's open source medical language model, is based on the MoE architecture of Ling-flash-2.0. It has 100B total parameters and 6.1B activation parameters. The inference speed exceeds 200 tokens/s and supports 128K context. Ranked first in the HealthBench benchmark test. After three-stage training, it has strong medical knowledge and complex diagnosis and treatment reasoning capabilities, suitable for complex case analysis and daily health questions and answers.
AntAngelMed, Ant Health's open source medical language model, is based on the MoE architecture of Ling-flash-2.0. It has 100B total parameters and 6.1B activation parameters. The inference speed exceeds 200 tokens/s and supports 128K context. Ranked first in the HealthBench benchmark test. After three-stage training, it has strong medical knowledge and complex diagnosis and treatment reasoning capabilities, suitable for complex case analysis and daily health questions and answers.