qwen3_5_vl_text

Model type	qwen3_5_vl_text
Class	Qwen35VLTextModel
Task	hybrid-text-generation
Source	models/qwen35.py

Description

Qwen3.5-VL text-only decoder.

Extracts the text backbone from the Qwen3.5-VL multimodal model. Strips language_model. weight prefixes and drops visual. keys.

Usage

mobius build --model <MODEL_ID> output_dir/

from mobius import build

model = build("<MODEL_ID>")