qwen2_vl

Model type	qwen2_vl
Class	Qwen2VLCausalLMModel
Task	qwen-vl
Source	models/qwen_vl.py

Description

Qwen2-VL vision-language model (3-model split).

Same 3-model architecture as Qwen2.5-VL but with:

• Qwen2VLVisionModel (LayerNorm + FCMLP, no windowed attention)

• Same text decoder and embedding model

Usage

mobius build --model <MODEL_ID> output_dir/

from mobius import build

model = build("<MODEL_ID>")