transformers.js
Add support for new Qwen VL models (Qwen2.5-VL, Qwen3-VL, Qwen3.5, and Qwen3.5 MoE)
#1551
Merged
Merged
Add support for new Qwen VL models (Qwen2.5-VL, Qwen3-VL, Qwen3.5, and Qwen3.5 MoE) #1551
xenova
merged
7 commits into
main
from
new-qwen-models
Move Qwen-specific image processing logic to image_processing_qwen2_v…
d3571251
use logger.info if dtype/device unspecified
3d131d6f
Update default logLevel
450d099d
Add hook for updating ORT logging when transformers.js log changes
862069f2
Formatting
d954b06c
Add support for Qwen2.5-VL, Qwen3-VL, Qwen3.5, and Qwen3.5 MoE
5a158fbd
Support qwen3.5 models with linear attention
7acf4c0e
nico-martin
commented
on 2026-03-02
nico-martin
commented
on 2026-03-02
nico-martin
commented
on 2026-03-02
Login to write a write a comment.
Login via GitHub