Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
mispeech
/
midashenglm-7b-0804-fp32
like
77
Follow
Horizon Team, Xiaomi MiLM Plus
91
Audio-Text-to-Text
Safetensors
5 languages
midashenglm
multimodal
audio-language-model
audio
custom_code
arxiv:
2508.03983
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
2
main
midashenglm-7b-0804-fp32
/
fig
/
capabilities_plot_7b-1.png
Commit History
Upload figures
7c3ae10
verified
jimbozhang
commited on
Jul 29, 2025