stepfun-ai
/

Step3-VL-10B

Image-Text-to-Text

Model card Files Files and versions

Step3-VL-10B / vision_encoder.py

Commit History

Fix Transformers 5 compatibility for generation and RoPE cache

7ca32a5
verified

Bvicii commited on Jul 14

update import modules

a77f584
verified

Kangheng commited on Jan 19

fix extra param

99836ad
verified

Tingdan commited on Jan 19

remove some unuse code

f7bf7c1

luotingdan commited on Jan 16

add model deploy

049cfe1

luotingdan commited on Jan 14