Hugging Face's logo

temsa
/
IrishCore-GlobalPointer-ContextPII-135M-v1-rc5

Token Classification
ONNX
Safetensors
English
Irish
distilbert
pii-masking
globalpointer
dynamic-quantization
ireland
irish
gaelic
Model card Files
xet
 Community

IrishCore-GlobalPointer-ContextPII-135M-v1-rc5

IrishCore-GlobalPointer-ContextPII-135M-v1-rc5 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

rc5 is a decoder-hardening release over rc4: the weights and ONNX graph are unchanged, but the packaged decode policy now repairs contextual street-address and county spans that still leaked through in real Irish gov / HSE style text.

What changed in rc5:

  • apartment / unit / house-name street-address prefixes are recovered into the full STREET_ADDRESS span
  • explicit County ..., Contae ..., and gContae ... forms are recovered as COUNTY
  • public-office street spans like Allocation Centre: Kennedy Avenue, Carlow... are recovered cleanly
  • the added globalpointer_context_redteam_v1 suite is now 1.0000 on both full and q8 paths

A model-level continuation from the rc4 weights was trained locally, but it did not beat the released weights on the gated suites. The promoted rc5 therefore keeps the stronger rc4 weights and improves the bundled inference policy instead.

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
  • contextual street-address recovery
  • explicit county phrase recovery

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

Benchmarks

ONNX q8

Suite F1 Examples/s
Irish core 1.0000 84.4937
Irish extended 1.0000 104.2776
Demographic holdout v2 1.0000 103.9646
Gov contact policy v1 1.0000 67.0486
Gov chatbot red-team v2 0.9861 88.9338
Gov chatbot gap holdout v2 1.0000 76.5277
Context red-team v1 1.0000 92.5221
Multilingual PPSN overall 0.9333 143.6130
Multilingual PPSN label-only 1.0000 —

Comparison

| Model | Core F1 | Demographic Holdout v2 F1 | Gov Contact Policy v1 F1 | Context Red-Team v1 F1 | Multilingual F1 | Core examples/s | | --- | ---: | ---: | ---: | ---: | ---: | | ContextPII rc5 q8 | 1.0000 | 1.0000 | 1.0000 | 1.0000 | 0.9333 | 84.4937 | | ContextPII rc4 q8 | 0.9935 | 1.0000 | 1.0000 | — | 0.9333 | 61.4970 | | GlobalPointer rc4 q8 | 1.0000 | 0.6938 | 0.7843 | — | 0.9333 | 221.5743 | | DiffMask rc6 q8 | 0.9733 | — | — | — | 0.9274 | 130.3415 |

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

Additional q8 release checks shipped in this repo:

  • eval/q8_irish_numeric_qafix_v2.json: numeric false-positive guardrail suite, now 1.0000 F1
  • eval/q8_irish_gov_chatbot_redteam_user_v2.json: user-turn split, 1.0000 F1
  • eval/q8_irish_gov_chatbot_redteam_assistant_v2.json: assistant-turn split, 0.9677 F1
  • eval/q8_globalpointer_context_redteam_v1.json: contextual hardening suite for apartment-prefix street addresses, explicit County/Contae forms, and public-office address blocks, now 1.0000 F1

The remaining assistant split miss is a policy mismatch on a public office address/city block: this contextual line still masks Kennedy Avenue, Carlow while the legacy assistant v2 gold only scores postcode and phone in that row.

  • 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.
  • globalpointer_context_redteam_v1 is the new contextual hardening benchmark for the cases that previously leaked through in real apartment / county / public-office text.
  • 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-rc5   --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-rc5   --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. The remaining multilingual overall gap is mostly driven by valid person-name masking in benchmark rows that only score PPSN. If you need a stricter non-Irish name policy, test on your own corpora before promoting beyond rc.

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

Repo Stack Full Core F1 Q8 Core F1 Q8 Multilingual PPSN F1 Q8 Core ex/s
temsa/IrishCore-GlobalPointer-ContextPII-4L-122M-v1-rc6 4-layer GlobalPointer distilled fast student 1.0000 1.0000 0.9333 282.9
temsa/IrishCore-GlobalPointer-ContextPII-4L-122M-v1-rc5 4-layer GlobalPointer distilled fast student 1.0000 1.0000 0.9333 282.9
temsa/IrishCore-GlobalPointer-ContextPII-4L-122M-v1-rc3 4-layer GlobalPointer distilled fast student 1.0000 1.0000 0.9333 317.9
temsa/IrishCore-GlobalPointer-ContextPII-4L-122M-v1-rc2 4-layer GlobalPointer distilled fast student 1.0000 1.0000 0.9333 292.5
temsa/IrishCore-GlobalPointer-ContextPII-4L-122M-v1-rc1 4-layer GlobalPointer distilled fast student 1.0000 1.0000 0.9333 337.3
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc29 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 232.7
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc28 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 232.7
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc25 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 212.1
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc24 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 278.9
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc23 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 237.6
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc22 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 106.8
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc21 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 150.8
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc20 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 181.9
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc19 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 73.1
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc18 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 126.2
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc17 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 125.5
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc16 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 125.5
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc15 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 125.5
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc14 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 119.2
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc13 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 126.1
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc12 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 73.6
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc11 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 94.1
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc10 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 125.8
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc9 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 119.8
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc8 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 128.9
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc7 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 89.0
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc6 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 89.0
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc5 GlobalPointer raw-only + context labels 1.0000 1.0000 0.9333 84.5
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc4 GlobalPointer raw-only + context labels 0.9935 0.9935 0.9333 61.5
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc3 GlobalPointer raw-only + context labels 0.9935 0.9935 0.9333 61.5
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc2 GlobalPointer raw-only + context labels 0.9935 0.9935 0.9222 61.5
temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc1 GlobalPointer raw-only + context labels 0.9935 0.9935 0.9222 61.5
temsa/IrishCore-GlobalPointer-135M-v1-rc4 GlobalPointer raw-only span-matrix 1.0000 1.0000 0.9333 221.6
temsa/IrishCore-GlobalPointer-135M-v1-rc3 GlobalPointer raw-only span-matrix 1.0000 1.0000 0.9213 204.9
temsa/IrishCore-GlobalPointer-135M-v1-rc2 GlobalPointer raw-only span-matrix 0.9934 0.9934 0.9326 231.2
temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc8 Raw-only token-span 0.9737 0.9737 0.9176 46.1
temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc7 Hybrid classifier + generated scanner spec 1.0000 0.9934 1.0000 30.0
temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc6 Hybrid classifier + repair decoders 1.0000 0.9934 1.0000 29.5
temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc5 Hybrid classifier + repair decoders 0.9737 0.9669 0.9333 34.4
temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc4 Hybrid classifier + repair decoders 0.9870 0.9740 0.9600 114.2
temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc3 Hybrid classifier + repair decoders 0.9806 0.9677 0.9333 44.9
temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc2 Hybrid classifier + repair decoders 0.9554 0.9615 0.7887 119.1
temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v1 Hybrid classifier baseline 0.9530 0.9333 0.9882 103.3
temsa/IrishCore-DiffMask-135M-v1-rc6 DiffMask token-span, scanner-free 0.9801 0.9733 0.9274 130.3
temsa/IrishCore-DiffMask-135M-v1-rc5 DiffMask token-span, scanner-free 0.9733 0.9733 0.9379 249.2
temsa/IrishCore-DiffMask-135M-v1-rc4 DiffMask token-span, scanner-free 0.9733 0.9733 0.9371 29.5
temsa/IrishCore-DiffMask-135M-v1-rc3 DiffMask token-span, scanner-free 0.9664 0.9664 0.9591 30.0
temsa/IrishCore-DiffMask-135M-v1-rc2 DiffMask token-span, scanner-free 0.9664 0.9664 0.9212 247.1
temsa/IrishCore-DiffMask-135M-v1-rc1 DiffMask token-span, scanner-free 0.9801 0.9934 0.9412 251.2

Irish Core PII: Other Public Checkpoints

Repo Stack Full Core F1 Q8 Core F1 Q8 Multilingual PPSN F1 Notes
temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc1 Hybrid classifier prototype 0.9487 — — Predates the public q8 artifact.

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

Repo Artifact Irish Large F1 Multilingual PPSN F1 User Raw F1 QA v8 F1 CPU ex/s
temsa/OpenMed-mLiteClinical-IrishPPSN-135M-v1 fp32 canonical checkpoint 0.8979 0.9704 0.8000 0.7385 57.4
temsa/OpenMed-mLiteClinical-IrishPPSN-135M-v1-fp16 fp16 CPU/GPU artifact — 0.9704 0.8000 0.7385 45.8
temsa/OpenMed-mLiteClinical-IrishPPSN-135M-v1-q8 dynamic int8 CPU artifact — 0.9040 — — 132.1

PPSN-Only: Historical Public Checkpoints

Repo Main Published Metrics Notes
temsa/OpenMed-PPSN-mLiteClinical-v1 same as canonical fp32 repo: multilingual 0.9704, user raw 0.8000 Legacy alias; prefer temsa/OpenMed-mLiteClinical-IrishPPSN-135M-v1.
temsa/OpenMed-PPSN-v6-raw-rc2 irish_reg_v5 0.8750; user_raw 0.8000; qa_v8 0.7385 Raw PPSN-only research checkpoint; no packaged multilingual CPU benchmark row.
temsa/OpenMed-PPSN-v5_1 irish_large_v2 raw 0.9285; qa_v6 hybrid strict 1.0000 Hybrid PPSN-only checkpoint; predates the canonical multilingual suite packaging.
temsa/OpenMed-PPSN-v5 irish_reg_v5 raw 0.8235; irish_reg_v5 hybrid strict 1.0000 Hybrid PPSN-only checkpoint; predates the canonical multilingual suite packaging.
temsa/OpenMed-PPSN-v4 synthetic non-PPSN drift check only Predates the current PPSN eval suite; no packaged apples-to-apples multilingual CPU row.

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.

Downloads last month
280
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
Token Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support