mmp2055/qwen3.5-9b-claude-4.6-os-av-h-uncensored-think-d_au-imat-bughunter-v6

document /adapter for fine-tuners

add LoRA adapter for fine-tuners (composition/re-merge)

highlight 'NOT A SUBSTITUTE FOR PRIMARY RESEARCH' warning

clarify: full 262k context runs fine on 32 GB Apple Silicon

set pipeline_tag to image-text-to-text

document vision support via mmproj-F32 (inherited from base)

add mmproj-F32 for vision support

translate model card to English + add recommended agent link

add Q4_K_M GGUF

add model card

initial commit