--- language: - en - ga license: apache-2.0 pipeline_tag: token-classification tags: - pii-masking - token-classification - globalpointer - onnx - dynamic-quantization - ireland - irish - gaelic --- # IrishCore-GlobalPointer-ContextPII-135M-v1-rc15 `IrishCore-GlobalPointer-ContextPII-135M-v1-rc15` is the current expanded-label raw-only PII masking release for Irish public-sector, HSE, and citizen-support flows. It keeps the same DistilBERT-size GlobalPointer span extractor family as `temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc14`, but ships a stronger bundled decoder for contextual Irish/English address, location, and name recovery while preserving the broader contextual masking behavior from rc14. 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` ## Positioning `rc15` is a decoder-hardening release over `rc14`. - weights unchanged - ONNX graph unchanged - no external scanner or validator added - deployment path still single-pass span extraction plus deterministic `[PII:LABEL]` replacement What changed in `rc15`: - lenited Gaelic address cues now recover full unit-plus-street spans like `Árasán 4, Cedar Court` - city recovery now handles city-before-county cases such as `Clonakilty, Co. Cork` and `Kildare Town, Co. Kildare` - county recovery now accepts generic `Co.` forms while avoiding the earlier `Contae na Mí` regression from field-style rescue - the decoder now recovers business-centre style address blocks like `Unit 5, Riverpark Business Centre` - structured-cue name recovery now handles prose forms like `Anne-Marie O'Connor-Smyth, PPSN ...` - `globalpointer_context_redteam_v8` is `1.0000` at both IoU 0.5 and exact-boundary matching on full and q8 paths while `globalpointer_context_redteam_v7` remains `1.0000` 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. ## Benchmarks ### ONNX q8 | Suite | F1 | Examples/s | | --- | ---: | ---: | | Irish core | 1.0000 | 125.5054 | | Gov contact policy v1 | 1.0000 | 74.3676 | | Gov chatbot red-team v2 | 0.9861 | 74.9871 | | Context red-team v8 | 1.0000 | 102.1626 | | Context red-team v7 | 1.0000 | 115.8655 | | Multilingual PPSN overall | 0.9333 | 120.6708 | | Multilingual PPSN label-only | 1.0000 | — | | Multilingual PPSN label-only | 1.0000 | — | ### Comparison | Model | Core F1 | Gov Contact Policy v1 F1 | Context Red-team v8 F1 | Multilingual F1 | Core examples/s | | --- | ---: | ---: | ---: | ---: | ---: | | ContextPII rc15 q8 | 1.0000 | 1.0000 | 1.0000 | 0.9333 | 125.5054 | | ContextPII rc14 q8 | 1.0000 | 1.0000 | — | 0.9333 | 119.2240 | | ContextPII rc13 q8 | 1.0000 | 1.0000 | — | 0.9333 | 126.0878 | ## Evaluation Notes Additional q8 release checks shipped in this repo: - `eval/q8_globalpointer_context_redteam_v8.json`: contextual regression suite for lenited Gaelic address cues, business-centre address blocks, generic city/county field cues, city-before-county recovery, and structured-cue hyphenated names, `1.0000` F1 in `rc15` - `eval/q8_globalpointer_context_redteam_v7.json`: contextual regression suite for generic county forms inside Irish address blocks, retained at `1.0000` F1 in `rc15` - `eval/q8_globalpointer_context_redteam_v6.json`: contextual regression suite for address cue variants, hyphenated DOBs, first-person bare age statements, role-cued lowercase names, and surname fields, retained from `rc12` - `eval/q8_globalpointer_context_redteam_v5.json`: contextual regression suite for slash-separated phones and 1-digit dotted/slashed DOB formats, retained from `rc11` - `eval/q8_globalpointer_location_coverage_v1.json`, `v2`, `v3`: Irish location coverage suites retained from `rc9` ## Usage ```bash python3 inference_mask_onnx.py --model temsa/IrishCore-GlobalPointer-ContextPII-135M-v1-rc15 --text "My surname is de Búrca, my PPSN is 1234567T, and my address is Árasán 4, Cedar Court, mBaile Átha Cliath, D08 XY12." ``` ## 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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v1) | Hybrid classifier baseline | 0.9530 | 0.9333 | 0.9882 | 103.3 | | [`temsa/IrishCore-DiffMask-135M-v1-rc6`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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`](https://huggingface.co/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.