model card: standard structure, measured facts, verified license declarations

docs: refresh measured performance (local retest 2026-08-18)

docs: descriptive model card

README: EXPERIMENTAL int8 bundle

Add EXPERIMENTAL int8 graph-compressed bundle (int8/)

embeddinggemma-300m Core AI fp32 static (seq 256), rebuilt on Linux box 2026-08-17; producer coreai-core 1.0.0b2; tokenizer bit-identical to mlboydaisuke@d9a60a18, main.mlirb +262 B (conversion is not byte-deterministic)

initial commit