bert-base-NER named-entity recognition (PER / ORG / LOC / MISC)

Browser-ready import artifacts for token-classification, produced by SkillSafe's reproducible converter (models/ in skillsafe.ai) from a pinned upstream source. Every byte here is derivable from that source plus the recipe below; nothing was edited by hand.

Provenance

Upstream	https://huggingface.co/dslim/bert-base-NER/tree/d1a3e8f13f8c3566299d95fcfc9a8d2382a9affc
Upstream SHA-256 / commit	d1a3e8f13f8c3566299d95fcfc9a8d2382a9affc
Recipe	recipes/bert-base-ner.yaml — sha256 083282ba04c75bdc8d0ebedc9e40b5e65c11a4ff42d0831d0bd04631c1c7bcb6
Toolchain	Python 3.12.13, torch 2.10.0, onnx 1.23.0, onnxruntime 1.30.0 on Darwin 25.6.0 arm64
Converted	2026-09-22T21:43:58+00:00

Files

file	class	size	SHA-256
config.json	bundle	0.00 MB	a5dc77a0d60dadf5645103017f3c7b8ece4ef1b450bc1ea68e17da1d3ae7e515
onnx/model.onnx	registry (fp32)	411.20 MB	963039b81eec5b33e23d84826ccdf1e8f8ada776f320e692113034cfae384617
special_tokens_map.json	bundle	0.00 MB	303df45a03609e4ead04bc3dc1536d0ab19b5358db685b6f3da123d05ec200e3
tokenizer_config.json	bundle	0.00 MB	4c052d60b505817149a29e88c5292d7779ddecfadbfc6208729e61403ec558ba
vocab.txt	bundle	0.20 MB	eeaa9875b23b04b4c54ef759d03db9d1ba1554838f8fb26c5d96fa551df93d02

registry files are parameter files served from models.skillsafe.ai once vetted; bundle files ship inside an app; registry-shared is a runtime library reused by every model of the same architecture.

Verification

Imported as published upstream (no conversion). Each file is pinned by SHA-256 to its source; every ONNX file passed onnx.checker and a CPU smoke run under onnxruntime with zero-filled inputs at the declared shapes:

file	inputs	outputs	ms
onnx/model.onnx	input_ids[1, 8], attention_mask[1, 8], token_type_ids[1, 8]	logits[1, 8, 9]	6.7

Use in the browser

import * as ort from "onnxruntime-web";
const session = await ort.InferenceSession.create("https://huggingface.co/skillsafe-ai/bert-base-ner/resolve/main/onnx/model.onnx", { executionProviders: ["webgpu", "wasm"] });

Contract (onnx/model.onnx): input input_ids int64 ['batch_size', 'sequence_length'], attention_mask int64 ['batch_size', 'sequence_length'], token_type_ids int64 ['batch_size', 'sequence_length'] → output logits float32 ['batch_size', 'sequence_length', 9]. Opset 11.

Licence and attribution

bert-base-NER: David S. Lim, MIT License. https://huggingface.co/dslim/bert-base-NER — the repo's own ONNX export.

Licence: MIT — notice: https://huggingface.co/dslim/bert-base-NER/blob/main/README.md. The conversion recipe and this model card are part of the SkillSafe repository and carry its licence; the weights remain under the upstream licence above.

The full manifest.json in this repo records the recipe, sources, toolchain (including the uv.lock hash) and per-file verification numbers.