[Mirror] Add Gemma3n multimodal support with MobileNetV5 vision encoder#64

Open

ngxson wants to merge 22 commits intongxson:masterfrom

simrnsingh:feat-gemma3n-vision

Commits on Dec 19, 2025

Add Gemma3nVisionModel - MobileNetV5 vision encoder convertor to convert_hf_to_gguf.py. Add gemma3n to vision projectors in gguf-py/gguf/constants.py.
simrnsingh
committed

Commits on Dec 20, 2025

Commits on Dec 22, 2025

Remove obsolete comments
simrnsingh
committed

Commits on Dec 26, 2025

- convert_hf_to_gguf.py & constants.py & tensor_mapping.py: Use explicit mapping: Custom map for double indexed blocks and tensor_mapping.py for rest
simrnsingh
committed
- Rename tensors to v.conv..., v.blk..., v.msfa... to better align with already existing terminology
simrnsingh
committed
Fix stem conv bias name
simrnsingh
committed

Commits on Dec 27, 2025