Hugging Face's logo

OpenMOSS-Team
/
MOSS-VL-Base-0708

Video-Text-to-Text
Transformers
Safetensors
English
Chinese
moss_vl
feature-extraction
Base
Video-Understanding
Image-Understanding
MOSS-VL
OpenMOSS
multimodal
video
vision-language
custom_code
Model card Files
xet
 Community
CCCCyx commited on
Commit
417395c
·
verified ·
1 Parent(s): ba1bee7

fix: apply query RoPE in cross-attention when reusing cached vision KV during decode

Browse files
Files changed (1) hide show
  1. modeling_moss_vl.py +0 -0
modeling_moss_vl.py CHANGED
The diff for this file is too large to render. See raw diff