temsa commited on
Commit
3f2710e
·
verified ·
1 Parent(s): 33d9b3a

Update model card portfolio benchmarks

Browse files
Files changed (1) hide show
  1. README.md +60 -0
README.md CHANGED
@@ -301,3 +301,63 @@ Notes:
301
  - Base model: `OpenMed/OpenMed-PII-mLiteClinical-Base-135M-v1`
302
  - The derivative release remains subject to the attribution terms of the upstream datasets listed above.
303
  - See `NOTICE`, `training_sources.json`, and `eval/benchmark_summary.json` for provenance and benchmark details.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
301
  - Base model: `OpenMed/OpenMed-PII-mLiteClinical-Base-135M-v1`
302
  - The derivative release remains subject to the attribution terms of the upstream datasets listed above.
303
  - See `NOTICE`, `training_sources.json`, and `eval/benchmark_summary.json` for provenance and benchmark details.
304
+
305
+ <!-- portfolio-comparison:start -->
306
+ ## Portfolio Comparison
307
+
308
+ Updated: `2026-03-14`.
309
+
310
+ Use this section for the fastest public comparison across the `temsa` PII masking portfolio.
311
+
312
+ - The first core table only includes public checkpoints that ship both comparable q8 accuracy and q8 CPU throughput.
313
+ - The first PPSN table only includes public artifacts that ship comparable PPSN accuracy and CPU throughput.
314
+ - Missing cells in the archive tables mean the older release did not ship that metric in its public bundle.
315
+ - DiffMask rows use the reconciled `clean_single_pass` harness that matches the deployed runtime.
316
+
317
+ ### Irish Core PII: Comparable Public Checkpoints
318
+
319
+ | Repo | Stack | Full Core F1 | Q8 Core F1 | Q8 Multilingual PPSN F1 | Q8 Core ex/s |
320
+ |---|---|---:|---:|---:|---:|
321
+ | [`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 |
322
+ | [`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 |
323
+ | [`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 |
324
+ | [`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 |
325
+ | [`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 |
326
+ | [`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 |
327
+ | [`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 |
328
+ | [`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 |
329
+ | [`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 |
330
+ | [`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 |
331
+
332
+ ### Irish Core PII: Other Public Checkpoints
333
+
334
+ | Repo | Stack | Full Core F1 | Q8 Core F1 | Q8 Multilingual PPSN F1 | Notes |
335
+ |---|---|---:|---:|---:|---|
336
+ | [`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 | — | Public bundle ships no comparable q8 throughput or multilingual row. |
337
+ | [`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 | — | Public bundle ships no comparable q8 throughput or multilingual row. |
338
+ | [`temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc4`](https://huggingface.co/temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc4) | Hybrid classifier + repair decoders | 0.9870 | 0.9804 | 0.9600 | Public bundle ships no comparable q8 throughput row. |
339
+ | [`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. |
340
+ | [`temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v1`](https://huggingface.co/temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v1) | Hybrid classifier baseline | 0.9530 | — | 0.9882 | Public bundle ships q8 multilingual scores but no q8 core-overall or q8 core throughput row. |
341
+
342
+ 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.
343
+
344
+ ### PPSN-Only: Comparable Public Artifacts
345
+
346
+ | Repo | Artifact | Irish Large F1 | Multilingual PPSN F1 | User Raw F1 | QA v8 F1 | CPU ex/s |
347
+ |---|---|---:|---:|---:|---:|---:|
348
+ | [`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 |
349
+ | [`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 |
350
+ | [`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 |
351
+
352
+ ### PPSN-Only: Historical Public Checkpoints
353
+
354
+ | Repo | Main Published Metrics | Notes |
355
+ |---|---|---|
356
+ | [`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`. |
357
+ | [`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. |
358
+ | [`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. |
359
+ | [`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. |
360
+ | [`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. |
361
+
362
+ If you need one CPU-first Irish core model today, compare `OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc8` 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.
363
+ <!-- portfolio-comparison:end -->