Instructions to use DataFog/pii-en-65m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DataFog/pii-en-65m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="DataFog/pii-en-65m")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("DataFog/pii-en-65m") model = AutoModelForTokenClassification.from_pretrained("DataFog/pii-en-65m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download LICENSING.md from DataFog/pii-en-65m: direct link, hf CLI and curl.
- Browser
- Download file 1.54 kB
-
https://huggingface.co/DataFog/pii-en-65m/resolve/4b5183087ce28e791070e84a7fd936ed7e81886a/LICENSING.md
- Command line
-
hf download hf://DataFog/pii-en-65m@4b5183087ce28e791070e84a7fd936ed7e81886a/LICENSING.md
-
curl -L -o LICENSING.md https://huggingface.co/DataFog/pii-en-65m/resolve/4b5183087ce28e791070e84a7fd936ed7e81886a/LICENSING.md
Release licensing
DataFog release contributions and weights use Apache-2.0 (LICENSE); this is a release license choice, not a pre-existing license discovered in the prototype. The pretrained backbone is Apache-2.0, confirmed by its pinned upstream card. Nemotron-PII is CC-BY-4.0; preserve NOTICE and dataset attribution with redistribution. Raw data is not included.
The unchanged ARM bundle retains ONNX Runtime's MIT license and ThirdPartyNotices, ort MIT/Apache-2.0 texts and tokenizers Apache-2.0 text. Additional Cargo package notice files are preserved in licenses/cargo; the inventory includes all locked packages and nested vendored notices. This is a machine-collected inventory, not a legal opinion or a binary linkage attestation.
r-efi 5.3.0 declares MIT OR Apache-2.0 in its Cargo metadata but supplies no standalone license text in its cached package. It is not linked into the macOS runtime; the top-level Apache-2.0 text is available. Before distributing a target that links it, acquire/retain its upstream license notices. Candidate platform binaries must carry their actual dependency inventory and runtime notices, and pass native qualification. Third-party terms remain in effect independently of the root license.
Upstream sources: https://huggingface.co/distilbert/distilbert-base-cased/tree/6ea81172465e8b0ad3fddeed32b986cdcdcffcf0 ; https://huggingface.co/datasets/nvidia/Nemotron-PII/tree/b70ffaf5ff39e079776134c5bf4381f00a9fd1ed ; https://github.com/microsoft/onnxruntime ; https://github.com/pykeio/ort .