Refresh GGUF metadata for confucius4_r2t2 and update usage documentation

Re-embed the schema-v1 spec after the community-layout compliance pass (max_tokens naming, status=community)

Regenerate GGUF with the schema-v1 model spec embedded (fully standalone option contract; removes the legacy-spec warning)

Add Confucius4-R2T2 GGUF: Q8_0 (2.31 GiB) and F16 (3.81 GiB) for audio.cpp, with embedded sidecars and model spec