names/: FastPDN NER — Polish PII

Source: ArkadiuszPawlak/fastpdn-ner-polish-pii, revision 636c57fe77b0afad8f065e7c76243dc051437035.
License: CC-BY-4.0.
Attribution: "FastPDN NER — Polish PII (ONNX)" by ArkadiuszPawlak, fine-tuned from clarin-pl/FastPDN on filtered KPWr (clarin-pl/kpwr-ner) plus LLM-synthetic data. Upstream model card README.md sha256 9ca776b1157e5dedfb9d404ee17a584ebfc80f4dc426beb68f69200a52522c6f, kept unchanged as UPSTREAM_README.md because the upstream repo is no longer publicly available (checked 2026-10-30).

Changes

config.json and tokenizer.json unchanged.
model.safetensors is upstream model.onnx (FP32, sha256 11924bfd20eb478ee614e5e1184536825db4747753d341af7c04b940efa84645) converted by convert.py (sha256 a698bc993b253fc70d960aa14af37a5088afb79c77dae70557c7056ce394333e): 199 tensors copied, 73 linear weights transposed from ONNX [in, out] to torch [out, in], no value changed. convert.py is included: it reads the upstream snapshot at that revision from the default Hugging Face cache and is create-only, so run a copy outside names/. A rerun under another safetensors version can give a different file sha256 with every tensor identical: only the __metadata__ key order differs.
Review Gate 14, on 1,000 documents (1,714 windows, 614,466 tokens): torch FP32 against ONNX Runtime FP32, max absolute logit difference 3.4e-4 (within 1e-3), every token's argmax identical, every person range identical.
NERGAL uses only the PERSON, PERSON_F and PERSON_L tags, masked as [PERSON].

File	sha256
`config.json`	`3cef51cd7d184478adbdec9f68730db279386fe145cb32473a0622edea923578`
`model.safetensors`	`2fa84ec6abd0c1b12ba0ba1548e89c9fca36fc58f03e66074db423b0e98ec8e6`
`tokenizer.json`	`3a690c2d605076ad3901d946d4c0145fbfb19fef2f01370c7388430aa9f31edf`
`convert.py`	`a698bc993b253fc70d960aa14af37a5088afb79c77dae70557c7056ce394333e`
`UPSTREAM_README.md`	`9ca776b1157e5dedfb9d404ee17a584ebfc80f4dc426beb68f69200a52522c6f`
`NOTICE.md`	this file