MiDashengLM-7B-0804 is a multimodal speech language model with 7B parameters released by Xiaomi, which supports audio understanding and text generation tasks and is suitable for inference and fine-tuning in general scenarios.

MultimodalSafetensorsMultiple Languages

MiDashengLM is an efficient audio understanding model. With the help of universal audio captioning technology, it can excellently complete various audio understanding tasks and shows outstanding performance and efficiency. This model outperforms similar models in multiple key audio understanding tasks, with high - efficiency inference speed and comprehensive audio understanding ability.

MultimodalSafetensorsMultiple Languages

Mi Dasheng Language Model is an efficient audio language model that achieves comprehensive audio understanding through subtitle-based alignment. This model has achieved leading performance in multiple audio understanding benchmark tests while maintaining high inference efficiency, with a 3.2-fold increase in throughput and support for a batch size of up to 512.

MultimodalSafetensorsMultiple Languages