OpenMOSS-Team
/

MOSS-VL-Base-0708

Video-Text-to-Text

feature-extraction

Video-Understanding

Image-Understanding

vision-language

Model card Files Files and versions

MOSS-VL-Base-0708 / processing_moss_vl.py

Commit History

Sep 23

03:54
per-sample media budgets in processor; per-sample MRoPE position ids for batched vision inputs

CCCCyx

Verified signature
f337b2e

Sep 7

10:48
Unify MOSS-VL processor and inference preprocessing defaults⁠

CCCCyx

Verified signature
ba1bee7

Jul 13

13:16
Upload folder using huggingface_hub

CCCCyx

Verified signature
a2ae4e5