Precision fix per review: lead with 8.4x vs best-case ONNX deployment, not the easier 437x/219x comparisons; scope the claim to this workload/hardware

Fix base_model_relation: was inferred as quantized (wrong — this port stays fp32, nothing was quantized)

Fix: link real GitHub repo instead of dangling local paths

Initial publish: native C++ port of prajjwal1/bert-tiny (Sajal Labs exp11-14)

initial commit