Basic information
Model repository: inclusionAI/Ming-flash-omni-Preview
Organization: inclusionAI
Tasks: any-to-any
Architecture and runtime
Model type: bailingmm_moe_v2_lite
Architecture: BailingMM2NativeForConditionalGeneration
Libraries: pytorch, transformer, safetensors, diffusers, tensorflow
Base models: inclusionAI/Ling-flash-2.0
Current revision: master
License and update history
License: mit
Created: 2025-11-30
Last updated: 2026-10-07
Hardware requirements
Not filled in locally.
Download links
Not filled in locally.
Basic usage example
Not filled in locally.