Skip to main content

Module qwen3_5_vision

Module qwen3_5_vision 

Source
Expand description

Qwen3.5 vision encoder

Architecture: Conv3d patch embedding → 27 transformer blocks (2D RoPE on Q/K) → VisionPatchMerger (2×2 spatial merge) → out_hidden_size projection.

Output: [total_image_patches, out_hidden_size]

Structs§

Qwen3_5VisionConfig
Qwen3_5VisionEncoder