release aidev NEEDS REVIEW SIG 1/5

Xiaomi MiMo VL-7B-SFT published on Hugging Face

Xiaomi published MiMo-VL-7B-SFT, a vision-language model checkpoint, on Hugging Face under the MIT license. Tags indicate it is built on Qwen2.5-VL and uses the transformers library.

PUBLISHED2025-05-30
OBSERVED2026-08-11
AGE1y
SOURCES1
  • Pipeline: image-text-to-text
  • Library: transformers
  • License: MIT
  • arXiv: 2506.03569
  • Base model: Qwen2.5-VL
  • Endpoints compatible

COMMUNITY

No curated reactions recorded for this event. Facts and takes are kept in separate layers — community context is added by hand, never blended into the record above.