temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc1

IrishCore-GlobalPointer-ContextPII-135M-v1-rc1

IrishCore-GlobalPointer-ContextPII-135M-v1-rc1 is an expanded-label raw-only PII masking model for Irish public-sector and citizen-support flows.

It keeps the same DistilBERT-size GlobalPointer span extractor family as temsa/IrishCore-GlobalPointer-135M-v1-rc4, but adds contextual labels that the core model did not serve:

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

The model still covers the core Irish structured labels:

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

Positioning

Use this release when you need broader masking for Irish gov / HSE / citizen-support text, including user turns and assistant answers that contain:

• —personal address fragments
• —city / county
• —date of birth
• —age
• —official callback numbers or public-service mailbox emails that still need masking in assistant output

If you only need the narrower Irish-core structured label set and want maximum CPU throughput, temsa/IrishCore-GlobalPointer-135M-v1-rc4 remains the faster option.

Architecture

• —base encoder: OpenMed/OpenMed-PII-mLiteClinical-Base-135M-v1
• —extractor head: GlobalPointer-style typed span matrix
• —runtime: single-pass span extraction
• —output policy: deterministic bracket masking, for example [PII:PPSN]
• —deployment target: ONNX Runtime CPU with dynamic q8 per-channel quantization

This is not a generative model and does not rewrite text. It predicts typed spans and the provided inference scripts replace them with [PII:LABEL] placeholders.

Decoder Policy

The serving path is still raw-only in the sense that there is no external scanner/validator service. The repo does include bundled decoder repairs for highly structured spans:

• —PPSN normalization and overlap repair
• —passport cue-based repair
• —contextual date-of-birth repair
• —full-email recovery
• —contextual phone extension
• —Eircode recovery

These repairs live inside common.py and are part of the published inference path.

Benchmarks

ONNX q8

Comparison

Tradeoff:

• —this expanded-label line is materially better on contextual Irish masking tasks
• —it is slower than the core-only GlobalPointer line on CPU because it carries a broader label inventory and more decoder work

Evaluation Notes

• —globalpointer_demographic_patch_v2_test is the corrected held-out benchmark. The earlier v1 demographic patch contained invalid synthetic Eircodes in some rows.
• —irish_gov_contact_policy_v1 is the policy-aligned assistant-output benchmark for this release.
• —The legacy irish_gov_chatbot_redteam_v2 negatives still assume some public assistant contact details should not be masked. That assumption does not match this release's target policy.

Usage

Full checkpoint:

python3 inference_mask.py   --model temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc1   --text "I live at 14 Main Street, Dublin, Co. Dublin, D02 XY45 and my date of birth is 03/02/1991."

ONNX q8:

python3 inference_mask_onnx.py   --model temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc1   --text "Employment Permit documents can be sent to EPStamp4@enterprise.gov.ie."

Expected masking style:

I live at [PII:STREET_ADDRESS], [PII:CITY], [PII:COUNTY], [PII:POSTCODE] and my date of birth is [PII:DATE_OF_BIRTH].

Files

• —model.safetensors: full checkpoint
• —onnx/model_quantized.onnx: recommended CPU artifact
• —inference_mask.py: full-checkpoint inference
• —inference_mask_onnx.py: ONNX q8 inference
• —eval/benchmark_summary.json: machine-readable benchmark summary
• —training_sources.json: data provenance

Limitations

• —This release is Irish-first. Multilingual overall precision is still pulled down by extra name detections outside the primary Irish target domain.
• —The decoder deliberately prefers recall on structured Irish identifiers. If you need a stricter public-contact suppression policy, test on your own corpora before promoting beyond rc.

<!-- 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 -->