OpenMed/privacy-filter-nemotron-v2-mlx

OpenMed Privacy Filter Nemotron v2 - MLX BF16

A native MLX port of OpenMed/privacy-filter-nemotron-v2 for Apple Silicon PII detection and de-identification with OpenMed. This is the unquantized BF16 reference artifact. For the 8-bit sibling, see OpenMed/privacy-filter-nemotron-v2-mlx-8bit.

Family at a glance:

• PyTorch source: OpenMed/privacy-filter-nemotron-v2
• MLX BF16 (this repo): Apple Silicon, full precision, 2.6 GiB weights
• MLX 8-bit: OpenMed/privacy-filter-nemotron-v2-mlx-8bit - Apple Silicon, 1.4 GiB weights

At a glance

• Source checkpoint: OpenMed/privacy-filter-nemotron-v2
• OpenMed MLX repo: OpenMed/privacy-filter-nemotron-v2-mlx
• Label schema: 55 fine-grained Nemotron-style PII categories
• Output space: 221 BIOES classes (O plus B/I/E/S for each category)
• Languages: 20-language metadata from the source card: bg, cs, da, de, el, en, es, et, fi, fr, hr, hu, it, lt, lv, nl, pl, pt, ro, sk
• Weight format: safetensors
• Quantization: none (BF16 reference)

Q8 sibling validation

The 8-bit sibling was compared against this BF16 artifact on 10 golden PII samples. Decoded entity spans matched across all samples. Average Q8/BF16 argmax agreement was 99.55% with average logit MAE 0.1769; average local forward time was 14.2 ms for BF16 vs 7.9 ms for Q8.

What it does

This model is an MLX packaging of OpenMed/privacy-filter-nemotron-v2, the second-generation Nemotron-schema checkpoint with a broader training mix and a more recall-oriented adaptation recipe than the first Nemotron branch. It uses OpenAI's Privacy Filter architecture and predicts 221 BIOES classes (O plus B/I/E/S for each category). The OpenMed PrivacyFilterMLXPipeline runs BIOES-aware Viterbi decoding so callers receive grouped spans instead of raw token tags.

Label coverage highlights:

• Identity and demographics: first_name, last_name, age, gender, nationality, language
• Contact and address: email, phone_number, street_address, city, country, postcode
• Government and regulated IDs: ssn, national_id, tax_id, certificate_license_number
• Financial and secrets: account_number, credit_debit_card, cvv, pin, password, swift_bic
• Medical, workplace, online, vehicle, and time identifiers such as medical_record_number, employee_id, ipv4, url, license_plate, date, and time

The full label map is included in id2label.json.

Architecture

Field	Value
Source model type	openai_privacy_filter
Source architecture	OpenAIPrivacyFilterForTokenClassification
Hidden size	640
Transformer layers	8
Attention	Grouped-query attention (14 query heads / 2 KV heads, head_dim=64) with attention sinks
FFN	Sparse Mixture-of-Experts - 128 experts, top-4 routing, SwiGLU
Position encoding	YARN-scaled RoPE (rope_theta=150000, factor=32)
Context length	131,072 tokens (initial 4,096)
Tokenizer	o200k_base / tiktoken-compatible tokenizer assets, vocab 200,064
Output head	Linear(640 -> 221) with bias

File set

File	Size	Purpose
weights.safetensors	2.6 GiB	MLX weights
config.json	19.5 KiB	Model and OpenMed MLX runtime config
id2label.json	5.4 KiB	Numeric ID to BIOES label mapping
openmed-mlx.json	0.7 KiB	OpenMed MLX artifact manifest
tokenizer.json	27 MiB	Tokenizer asset kept with the artifact
tokenizer_config.json	0.2 KiB	Tokenizer metadata

The MLX runtime uses the tiktoken-compatible o200k_base tokenizer path. tokenizer.json and tokenizer_config.json are bundled so consumers can inspect the tokenizer assets and keep the artifact self-contained.

Quick start

With OpenMed

pip install -U "openmed[mlx]"

from openmed import extract_pii, deidentify
from openmed.core import OpenMedConfig

model_name = "OpenMed/privacy-filter-nemotron-v2-mlx"
text = (
    "Patient Sarah Johnson (DOB 03/15/1985), MRN 4872910, "
    "phone 415-555-0123, email sarah.johnson@example.com."
)

result = extract_pii(
    text,
    model_name=model_name,
    config=OpenMedConfig(backend="mlx"),
)
for ent in result.entities:
    print(ent.label, ent.text, round(ent.confidence, 4))

masked = deidentify(
    text,
    method="mask",
    model_name=model_name,
    config=OpenMedConfig(backend="mlx"),
)
print(masked.deidentified_text)

For non-MLX hosts, use the source PyTorch checkpoint OpenMed/privacy-filter-nemotron-v2.

Direct MLX usage

from huggingface_hub import snapshot_download
from openmed.mlx.inference import PrivacyFilterMLXPipeline

model_path = snapshot_download("OpenMed/privacy-filter-nemotron-v2-mlx")
pipe = PrivacyFilterMLXPipeline(model_path)

print(pipe("Email me at alice.smith@example.com after 5pm."))

Loading from a local snapshot

from openmed.mlx.models import load_model
import mlx.core as mx

model = load_model("/path/to/privacy-filter-nemotron-v2-mlx")
ids = mx.array([[1, 100, 200, 300]], dtype=mx.int32)
mask = mx.ones((1, 4), dtype=mx.bool_)
logits = model(ids, attention_mask=mask)
print(logits.shape)

Hardware notes

• Designed for Apple Silicon with MLX.
• CPU inference may work, but GPU-backed MLX on M-series Macs is the intended runtime.
• The Python package path is pip install -U "openmed[mlx]".

Credits

This artifact builds on:

• OpenMed/privacy-filter-nemotron-v2 by OpenMed
• openai/privacy-filter and OpenAI's opf training/evaluation tooling
• The datasets listed in the model-card metadata above
• Apple's MLX framework

License

The source checkpoint model card currently declares license: other; this MLX packaging follows that source license metadata. Review the source model card before redistribution.