temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc25

IrishCore-GlobalPointer-ContextPII-135M-v1-rc25

IrishCore-GlobalPointer-ContextPII-135M-v1-rc25 is the current expanded-label raw-only PII masking release for Irish public-sector, HSE, and citizen-support flows.

It keeps the same weights and ONNX graph as temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc24, but ships a stronger bundled contextual decoder path.

Positioning

rc25 is a runtime-only release over rc24.

• —weights unchanged
• —ONNX graph unchanged
• —no external scanner or validator added
• —deployment path still single-pass span extraction plus deterministic [PII:LABEL] replacement

Context labels served by this line:

• —STREET_ADDRESS
• —CITY
• —COUNTY
• —DATE_OF_BIRTH
• —AGE

Core labels retained:

• —PPSN
• —POSTCODE
• —PHONE_NUMBER
• —EMAIL
• —PASSPORT_NUMBER
• —ACCOUNT_NUMBER
• —BANK_ROUTING_NUMBER
• —SWIFT_BIC
• —CREDIT_DEBIT_CARD
• —FIRST_NAME
• —LAST_NAME

What Changed

• —fixed the fresh v18 holdout failures on compound Unit/Árasán + building + street address spans
• —removed the case code / cód poiblí street-address false positive family
• —removed the Irish month-name substring city false positive family such as Aibreán -> bre
• —preserved the Irish-first chatbot and contact-policy gates

Benchmarks

ONNX q8

Evaluation Notes

Additional q8 release checks shipped in this repo:

• —eval/q8_globalpointer_context_holdout_v18_exact.json: fresh unseen contextual holdout for public-office addresses, mixed public/private contacts, and Irish month-name negatives, now 1.0000
• —eval/q8_irish_gov_chatbot_gap_holdout_v2.json: Irish gov-chatbot holdout, now 1.0000
• —eval/q8_irish_gov_chatbot_redteam_v2.json: Irish gov-chatbot red-team suite, now 0.9861

Usage

python3 inference_mask_onnx.py --model temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc25 --text "My PPSN is 1234567T and my address is Unit 6, Harbour Point, 19 Railway Road, Portlaoise, County Laois, R32 AB12."

<!-- portfolio-comparison:start -->

Portfolio Comparison

Updated: 2026-03-16.

Use this section for the fastest public comparison across the temsa PII masking portfolio.

• —The first core table only includes public checkpoints that ship both comparable q8 accuracy and q8 CPU throughput.
• —The first PPSN table only includes public artifacts that ship comparable PPSN accuracy and CPU throughput.
• —Missing cells in the archive tables mean the older release did not ship that metric in its public bundle.
• —DiffMask rows use the reconciled clean_single_pass harness that matches the deployed runtime.
• —GlobalPointer rows use the public raw-only span-matrix release bundle and its packaged q8 ONNX artifact.
• —The same content is shipped as PORTFOLIO_COMPARISON.md inside each public model repo.

Irish Core PII: Comparable Public Checkpoints

Irish Core PII: Other Public Checkpoints

Finance-boundary q8 F1 is 1.0000 for OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc6, OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc7, OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc8, and all public IrishCore-DiffMask releases from rc1 to rc6. OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc5 ships 0.8750 on that public q8 suite.

PPSN-Only: Comparable Public Artifacts

PPSN-Only: Historical Public Checkpoints

If you need the strongest current raw-only Irish core model, start with IrishCore-GlobalPointer-135M-v1-rc4. If you need the fastest CPU-first raw-only line, compare it against IrishCore-DiffMask-135M-v1-rc6. If you need a PPSN-only artifact, compare the canonical fp32, fp16, and q8 variants of OpenMed-mLiteClinical-IrishPPSN-135M-v1 directly in the table above. <!-- portfolio-comparison:end -->