Upload MLX packaging for privacy-filter-nemotron-mlx

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,136 @@
+---
+license: apache-2.0
+base_model: OpenMed/privacy-filter-nemotron
+pipeline_tag: token-classification
+library_name: openmed
+tags:
+  - openmed
+  - mlx
+  - apple-silicon
+  - token-classification
+  - pii
+  - de-identification
+  - medical
+  - clinical
+  - privacy-filter
+  - nemotron
+---
+
+# OpenMed Privacy Filter (Nemotron) — MLX BF16
+
+A native [MLX](https://github.com/ml-explore/mlx) port of [`OpenMed/privacy-filter-nemotron`](https://huggingface.co/OpenMed/privacy-filter-nemotron) for fast, on-device PII detection on Apple Silicon. This BF16 artifact preserves the full source precision; for a smaller / faster sibling, see [`OpenMed/privacy-filter-nemotron-mlx-8bit`](https://huggingface.co/OpenMed/privacy-filter-nemotron-mlx-8bit).
+
+> **Private / early access.** Both this repo and the source checkpoint are private. You need explicit access to download.
+
+## What it does
+
+The model is a token classifier trained on OpenAI's open Privacy Filter architecture (the same `openai_privacy_filter` model type used by `openai/privacy-filter`). It tags each token in a string with a BIOES label across **55 PII span classes**, then a Viterbi pass over the BIOES grammar yields clean entity spans. Detected categories include:
+
+- Personal identifiers — `first_name`, `last_name`, `user_name`, `gender`, `age`, `date_of_birth`
+- Contact — `email`, `phone_number`, `fax_number`, `street_address`, `city`, `state`, `country`, `county`, `postcode`, `coordinate`
+- Government / legal IDs — `ssn`, `national_id`, `tax_id`, `certificate_license_number`
+- Financial — `account_number`, `bank_routing_number`, `credit_debit_card`, `cvv`, `pin`, `swift_bic`
+- Medical — `medical_record_number`, `health_plan_beneficiary_number`, `blood_type`
+- Workplace — `company_name`, `occupation`, `employee_id`, `customer_id`, `employment_status`, `education_level`
+- Online — `url`, `ipv4`, `ipv6`, `mac_address`, `http_cookie`, `api_key`, `password`, `device_identifier`
+- Demographic — `race_ethnicity`, `religious_belief`, `political_view`, `sexuality`, `language`
+- Vehicles — `license_plate`, `vehicle_identifier`
+- Time — `date`, `date_time`, `time`
+- Misc — `biometric_identifier`, `unique_id`
+
+<details>
+<summary>Full label schema (221 labels)</summary>
+
+The output space is `O` plus `B-`, `I-`, `E-`, `S-` for each of the 55 span classes (4 × 55 + 1 = 221). The runtime `PrivacyFilterMLXPipeline` runs Viterbi over this BIOES grammar, so the consumer sees clean grouped entities rather than raw token tags.
+
+The full `id2label.json` is shipped alongside the weights in this repo.
+</details>
+
+## Architecture
+
+| Field | Value |
+| --- | --- |
+| Source model type | `openai_privacy_filter` |
+| Source architecture | `OpenAIPrivacyFilterForTokenClassification` |
+| Hidden size | 640 |
+| Transformer layers | 8 |
+| Attention | Grouped-Query (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=150_000`, factor=32) |
+| Context length | 131,072 tokens (initial 4,096) |
+| Tokenizer | `o200k_base` (tiktoken) — vocab 200,064 |
+| Output head | Linear(640 → 221) with bias |
+
+## File set
+
+| File | Size | Purpose |
+| --- | --- | --- |
+| `weights.safetensors` | 2.6 GB | BF16 model weights in OpenMed-MLX layout |
+| `config.json` | 19 KB | Model + MLX runtime config |
+| `id2label.json` | 5.4 KB | Numeric ID → BIOES label string |
+| `openmed-mlx.json` | 0.7 KB | OpenMed MLX manifest (task, family, runtime hints) |
+| `tokenizer.json`, `tokenizer_config.json` | 27 MB | Source tokenizer files (kept for reference) |
+
+The MLX runtime uses `tiktoken` `o200k_base` directly for tokenization; the `tokenizer.json` is kept so consumers can inspect or re-tokenize via `transformers` if desired.
+
+## Usage
+
+```bash
+pip install "openmed[mlx]"
+```
+
+```python
+from huggingface_hub import snapshot_download
+from openmed.mlx.inference import PrivacyFilterMLXPipeline
+
+model_path = snapshot_download("OpenMed/privacy-filter-nemotron-mlx")
+pipe = PrivacyFilterMLXPipeline(model_path)
+
+print(pipe("Email me at alice.smith@example.com after 5pm."))
+# [{'entity_group': 'email',
+#   'score': 0.92,
+#   'word': 'alice.smith@example.com',
+#   'start': 12,
+#   'end': 35}]
+```
+
+The pipeline returns a list of dicts with `entity_group`, `score`, `word`, `start`, and `end` (character offsets into the input string).
+
+### Loading from a local snapshot
+
+```python
+from openmed.mlx.models import load_model
+import mlx.core as mx
+
+model = load_model("/path/to/privacy-filter-nemotron-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)   # shape (1, 4, 221)
+```
+
+## Hardware notes
+
+- Designed for Apple Silicon (M-series GPUs); CPU inference works but is slower.
+- Tested on macOS with `mlx>=0.18`, `mlx_lm>=0.31`. The MLX runtime in this repo is independent of `mlx_lm` (token classification, not causal LM).
+- Forward pass on a typical PII sentence (~10 tokens) takes ~14 ms on M-series GPU after warmup. For lower latency or smaller memory footprint, use the [`-mlx-8bit`](https://huggingface.co/OpenMed/privacy-filter-nemotron-mlx-8bit) sibling instead.
+
+## Conversion
+
+This repo was produced by [`openmed.mlx.convert`](https://github.com/maziyarpanahi/openmed) from the source HuggingFace checkpoint. The converter:
+
+1. Downloads `model.safetensors` from the source repo.
+2. Remaps the standard transformers state dict (`model.embed_tokens`, `self_attn.q_proj/k_proj/v_proj`, `mlp.experts.gate_up_proj`, `score`, …) into the OpenMed-MLX layout (`embedding.weight`, fused `block.X.attn.qkv.weight`, `block.X.mlp.swiglu.weight`, `unembedding.weight`, …).
+3. Writes an `openmed-mlx.json` manifest that pins the runtime contract: `task=token-classification`, `family=openai-privacy-filter`, `runtime.decode=bioes-viterbi`, `runtime.tokenizer=tiktoken`.
+
+For the quantized variant, the same path runs an additional `mlx.nn.quantize(..., bits=8, group_size=64, mode="affine")` pass over `embedding`, attention `qkv`/`out`, MoE `gate`, expert `swiglu`/`out`, and `unembedding`.
+
+## Credits
+
+- Source checkpoint: [`OpenMed/privacy-filter-nemotron`](https://huggingface.co/OpenMed/privacy-filter-nemotron)
+- Architecture: OpenAI Privacy Filter (open architecture, custom modeling code) adapted by OpenMed.
+- MLX conversion + runtime: OpenMed
+- Apple Silicon SDK: [Apple MLX](https://github.com/ml-explore/mlx)
+
+## License
+
+Apache 2.0 (matches the source checkpoint).

config.json

@@ -0,0 +1,809 @@
+{
+  "architectures": [
+    "OpenAIPrivacyFilterForTokenClassification"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "classifier_dropout": 0.0,
+  "default_n_ctx": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 199999,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 640,
+  "id2label": {
+    "0": "O",
+    "1": "B-account_number",
+    "2": "I-account_number",
+    "3": "E-account_number",
+    "4": "S-account_number",
+    "5": "B-age",
+    "6": "I-age",
+    "7": "E-age",
+    "8": "S-age",
+    "9": "B-api_key",
+    "10": "I-api_key",
+    "11": "E-api_key",
+    "12": "S-api_key",
+    "13": "B-bank_routing_number",
+    "14": "I-bank_routing_number",
+    "15": "E-bank_routing_number",
+    "16": "S-bank_routing_number",
+    "17": "B-biometric_identifier",
+    "18": "I-biometric_identifier",
+    "19": "E-biometric_identifier",
+    "20": "S-biometric_identifier",
+    "21": "B-blood_type",
+    "22": "I-blood_type",
+    "23": "E-blood_type",
+    "24": "S-blood_type",
+    "25": "B-certificate_license_number",
+    "26": "I-certificate_license_number",
+    "27": "E-certificate_license_number",
+    "28": "S-certificate_license_number",
+    "29": "B-city",
+    "30": "I-city",
+    "31": "E-city",
+    "32": "S-city",
+    "33": "B-company_name",
+    "34": "I-company_name",
+    "35": "E-company_name",
+    "36": "S-company_name",
+    "37": "B-coordinate",
+    "38": "I-coordinate",
+    "39": "E-coordinate",
+    "40": "S-coordinate",
+    "41": "B-country",
+    "42": "I-country",
+    "43": "E-country",
+    "44": "S-country",
+    "45": "B-county",
+    "46": "I-county",
+    "47": "E-county",
+    "48": "S-county",
+    "49": "B-credit_debit_card",
+    "50": "I-credit_debit_card",
+    "51": "E-credit_debit_card",
+    "52": "S-credit_debit_card",
+    "53": "B-customer_id",
+    "54": "I-customer_id",
+    "55": "E-customer_id",
+    "56": "S-customer_id",
+    "57": "B-cvv",
+    "58": "I-cvv",
+    "59": "E-cvv",
+    "60": "S-cvv",
+    "61": "B-date",
+    "62": "I-date",
+    "63": "E-date",
+    "64": "S-date",
+    "65": "B-date_of_birth",
+    "66": "I-date_of_birth",
+    "67": "E-date_of_birth",
+    "68": "S-date_of_birth",
+    "69": "B-date_time",
+    "70": "I-date_time",
+    "71": "E-date_time",
+    "72": "S-date_time",
+    "73": "B-device_identifier",
+    "74": "I-device_identifier",
+    "75": "E-device_identifier",
+    "76": "S-device_identifier",
+    "77": "B-education_level",
+    "78": "I-education_level",
+    "79": "E-education_level",
+    "80": "S-education_level",
+    "81": "B-email",
+    "82": "I-email",
+    "83": "E-email",
+    "84": "S-email",
+    "85": "B-employee_id",
+    "86": "I-employee_id",
+    "87": "E-employee_id",
+    "88": "S-employee_id",
+    "89": "B-employment_status",
+    "90": "I-employment_status",
+    "91": "E-employment_status",
+    "92": "S-employment_status",
+    "93": "B-fax_number",
+    "94": "I-fax_number",
+    "95": "E-fax_number",
+    "96": "S-fax_number",
+    "97": "B-first_name",
+    "98": "I-first_name",
+    "99": "E-first_name",
+    "100": "S-first_name",
+    "101": "B-gender",
+    "102": "I-gender",
+    "103": "E-gender",
+    "104": "S-gender",
+    "105": "B-health_plan_beneficiary_number",
+    "106": "I-health_plan_beneficiary_number",
+    "107": "E-health_plan_beneficiary_number",
+    "108": "S-health_plan_beneficiary_number",
+    "109": "B-http_cookie",
+    "110": "I-http_cookie",
+    "111": "E-http_cookie",
+    "112": "S-http_cookie",
+    "113": "B-ipv4",
+    "114": "I-ipv4",
+    "115": "E-ipv4",
+    "116": "S-ipv4",
+    "117": "B-ipv6",
+    "118": "I-ipv6",
+    "119": "E-ipv6",
+    "120": "S-ipv6",
+    "121": "B-language",
+    "122": "I-language",
+    "123": "E-language",
+    "124": "S-language",
+    "125": "B-last_name",
+    "126": "I-last_name",
+    "127": "E-last_name",
+    "128": "S-last_name",
+    "129": "B-license_plate",
+    "130": "I-license_plate",
+    "131": "E-license_plate",
+    "132": "S-license_plate",
+    "133": "B-mac_address",
+    "134": "I-mac_address",
+    "135": "E-mac_address",
+    "136": "S-mac_address",
+    "137": "B-medical_record_number",
+    "138": "I-medical_record_number",
+    "139": "E-medical_record_number",
+    "140": "S-medical_record_number",
+    "141": "B-national_id",
+    "142": "I-national_id",
+    "143": "E-national_id",
+    "144": "S-national_id",
+    "145": "B-occupation",
+    "146": "I-occupation",
+    "147": "E-occupation",
+    "148": "S-occupation",
+    "149": "B-password",
+    "150": "I-password",
+    "151": "E-password",
+    "152": "S-password",
+    "153": "B-phone_number",
+    "154": "I-phone_number",
+    "155": "E-phone_number",
+    "156": "S-phone_number",
+    "157": "B-pin",
+    "158": "I-pin",
+    "159": "E-pin",
+    "160": "S-pin",
+    "161": "B-political_view",
+    "162": "I-political_view",
+    "163": "E-political_view",
+    "164": "S-political_view",
+    "165": "B-postcode",
+    "166": "I-postcode",
+    "167": "E-postcode",
+    "168": "S-postcode",
+    "169": "B-race_ethnicity",
+    "170": "I-race_ethnicity",
+    "171": "E-race_ethnicity",
+    "172": "S-race_ethnicity",
+    "173": "B-religious_belief",
+    "174": "I-religious_belief",
+    "175": "E-religious_belief",
+    "176": "S-religious_belief",
+    "177": "B-sexuality",
+    "178": "I-sexuality",
+    "179": "E-sexuality",
+    "180": "S-sexuality",
+    "181": "B-ssn",
+    "182": "I-ssn",
+    "183": "E-ssn",
+    "184": "S-ssn",
+    "185": "B-state",
+    "186": "I-state",
+    "187": "E-state",
+    "188": "S-state",
+    "189": "B-street_address",
+    "190": "I-street_address",
+    "191": "E-street_address",
+    "192": "S-street_address",
+    "193": "B-swift_bic",
+    "194": "I-swift_bic",
+    "195": "E-swift_bic",
+    "196": "S-swift_bic",
+    "197": "B-tax_id",
+    "198": "I-tax_id",
+    "199": "E-tax_id",
+    "200": "S-tax_id",
+    "201": "B-time",
+    "202": "I-time",
+    "203": "E-time",
+    "204": "S-time",
+    "205": "B-unique_id",
+    "206": "I-unique_id",
+    "207": "E-unique_id",
+    "208": "S-unique_id",
+    "209": "B-url",
+    "210": "I-url",
+    "211": "E-url",
+    "212": "S-url",
+    "213": "B-user_name",
+    "214": "I-user_name",
+    "215": "E-user_name",
+    "216": "S-user_name",
+    "217": "B-vehicle_identifier",
+    "218": "I-vehicle_identifier",
+    "219": "E-vehicle_identifier",
+    "220": "S-vehicle_identifier"
+  },
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 640,
+  "label2id": {
+    "O": 0,
+    "B-account_number": 1,
+    "I-account_number": 2,
+    "E-account_number": 3,
+    "S-account_number": 4,
+    "B-age": 5,
+    "I-age": 6,
+    "E-age": 7,
+    "S-age": 8,
+    "B-api_key": 9,
+    "I-api_key": 10,
+    "E-api_key": 11,
+    "S-api_key": 12,
+    "B-bank_routing_number": 13,
+    "I-bank_routing_number": 14,
+    "E-bank_routing_number": 15,
+    "S-bank_routing_number": 16,
+    "B-biometric_identifier": 17,
+    "I-biometric_identifier": 18,
+    "E-biometric_identifier": 19,
+    "S-biometric_identifier": 20,
+    "B-blood_type": 21,
+    "I-blood_type": 22,
+    "E-blood_type": 23,
+    "S-blood_type": 24,
+    "B-certificate_license_number": 25,
+    "I-certificate_license_number": 26,
+    "E-certificate_license_number": 27,
+    "S-certificate_license_number": 28,
+    "B-city": 29,
+    "I-city": 30,
+    "E-city": 31,
+    "S-city": 32,
+    "B-company_name": 33,
+    "I-company_name": 34,
+    "E-company_name": 35,
+    "S-company_name": 36,
+    "B-coordinate": 37,
+    "I-coordinate": 38,
+    "E-coordinate": 39,
+    "S-coordinate": 40,
+    "B-country": 41,
+    "I-country": 42,
+    "E-country": 43,
+    "S-country": 44,
+    "B-county": 45,
+    "I-county": 46,
+    "E-county": 47,
+    "S-county": 48,
+    "B-credit_debit_card": 49,
+    "I-credit_debit_card": 50,
+    "E-credit_debit_card": 51,
+    "S-credit_debit_card": 52,
+    "B-customer_id": 53,
+    "I-customer_id": 54,
+    "E-customer_id": 55,
+    "S-customer_id": 56,
+    "B-cvv": 57,
+    "I-cvv": 58,
+    "E-cvv": 59,
+    "S-cvv": 60,
+    "B-date": 61,
+    "I-date": 62,
+    "E-date": 63,
+    "S-date": 64,
+    "B-date_of_birth": 65,
+    "I-date_of_birth": 66,
+    "E-date_of_birth": 67,
+    "S-date_of_birth": 68,
+    "B-date_time": 69,
+    "I-date_time": 70,
+    "E-date_time": 71,
+    "S-date_time": 72,
+    "B-device_identifier": 73,
+    "I-device_identifier": 74,
+    "E-device_identifier": 75,
+    "S-device_identifier": 76,
+    "B-education_level": 77,
+    "I-education_level": 78,
+    "E-education_level": 79,
+    "S-education_level": 80,
+    "B-email": 81,
+    "I-email": 82,
+    "E-email": 83,
+    "S-email": 84,
+    "B-employee_id": 85,
+    "I-employee_id": 86,
+    "E-employee_id": 87,
+    "S-employee_id": 88,
+    "B-employment_status": 89,
+    "I-employment_status": 90,
+    "E-employment_status": 91,
+    "S-employment_status": 92,
+    "B-fax_number": 93,
+    "I-fax_number": 94,
+    "E-fax_number": 95,
+    "S-fax_number": 96,
+    "B-first_name": 97,
+    "I-first_name": 98,
+    "E-first_name": 99,
+    "S-first_name": 100,
+    "B-gender": 101,
+    "I-gender": 102,
+    "E-gender": 103,
+    "S-gender": 104,
+    "B-health_plan_beneficiary_number": 105,
+    "I-health_plan_beneficiary_number": 106,
+    "E-health_plan_beneficiary_number": 107,
+    "S-health_plan_beneficiary_number": 108,
+    "B-http_cookie": 109,
+    "I-http_cookie": 110,
+    "E-http_cookie": 111,
+    "S-http_cookie": 112,
+    "B-ipv4": 113,
+    "I-ipv4": 114,
+    "E-ipv4": 115,
+    "S-ipv4": 116,
+    "B-ipv6": 117,
+    "I-ipv6": 118,
+    "E-ipv6": 119,
+    "S-ipv6": 120,
+    "B-language": 121,
+    "I-language": 122,
+    "E-language": 123,
+    "S-language": 124,
+    "B-last_name": 125,
+    "I-last_name": 126,
+    "E-last_name": 127,
+    "S-last_name": 128,
+    "B-license_plate": 129,
+    "I-license_plate": 130,
+    "E-license_plate": 131,
+    "S-license_plate": 132,
+    "B-mac_address": 133,
+    "I-mac_address": 134,
+    "E-mac_address": 135,
+    "S-mac_address": 136,
+    "B-medical_record_number": 137,
+    "I-medical_record_number": 138,
+    "E-medical_record_number": 139,
+    "S-medical_record_number": 140,
+    "B-national_id": 141,
+    "I-national_id": 142,
+    "E-national_id": 143,
+    "S-national_id": 144,
+    "B-occupation": 145,
+    "I-occupation": 146,
+    "E-occupation": 147,
+    "S-occupation": 148,
+    "B-password": 149,
+    "I-password": 150,
+    "E-password": 151,
+    "S-password": 152,
+    "B-phone_number": 153,
+    "I-phone_number": 154,
+    "E-phone_number": 155,
+    "S-phone_number": 156,
+    "B-pin": 157,
+    "I-pin": 158,
+    "E-pin": 159,
+    "S-pin": 160,
+    "B-political_view": 161,
+    "I-political_view": 162,
+    "E-political_view": 163,
+    "S-political_view": 164,
+    "B-postcode": 165,
+    "I-postcode": 166,
+    "E-postcode": 167,
+    "S-postcode": 168,
+    "B-race_ethnicity": 169,
+    "I-race_ethnicity": 170,
+    "E-race_ethnicity": 171,
+    "S-race_ethnicity": 172,
+    "B-religious_belief": 173,
+    "I-religious_belief": 174,
+    "E-religious_belief": 175,
+    "S-religious_belief": 176,
+    "B-sexuality": 177,
+    "I-sexuality": 178,
+    "E-sexuality": 179,
+    "S-sexuality": 180,
+    "B-ssn": 181,
+    "I-ssn": 182,
+    "E-ssn": 183,
+    "S-ssn": 184,
+    "B-state": 185,
+    "I-state": 186,
+    "E-state": 187,
+    "S-state": 188,
+    "B-street_address": 189,
+    "I-street_address": 190,
+    "E-street_address": 191,
+    "S-street_address": 192,
+    "B-swift_bic": 193,
+    "I-swift_bic": 194,
+    "E-swift_bic": 195,
+    "S-swift_bic": 196,
+    "B-tax_id": 197,
+    "I-tax_id": 198,
+    "E-tax_id": 199,
+    "S-tax_id": 200,
+    "B-time": 201,
+    "I-time": 202,
+    "E-time": 203,
+    "S-time": 204,
+    "B-unique_id": 205,
+    "I-unique_id": 206,
+    "E-unique_id": 207,
+    "S-unique_id": 208,
+    "B-url": 209,
+    "I-url": 210,
+    "E-url": 211,
+    "S-url": 212,
+    "B-user_name": 213,
+    "I-user_name": 214,
+    "E-user_name": 215,
+    "S-user_name": 216,
+    "B-vehicle_identifier": 217,
+    "I-vehicle_identifier": 218,
+    "E-vehicle_identifier": 219,
+    "S-vehicle_identifier": 220
+  },
+  "max_position_embeddings": 131072,
+  "model_type": "openai_privacy_filter",
+  "num_attention_heads": 14,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 2,
+  "num_local_experts": 128,
+  "output_router_logits": false,
+  "pad_token_id": 199999,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_theta": 150000.0,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": 128,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.0.dev0",
+  "use_cache": true,
+  "vocab_size": 200064,
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "model.onnx": 3,
+      "model_fp16.onnx": 2,
+      "model": 1
+    }
+  },
+  "num_labels": 221,
+  "opf_metadata": {
+    "category_version": "nemotron_fine_v1",
+    "encoding": "o200k_base",
+    "span_class_names": [
+      "O",
+      "account_number",
+      "age",
+      "api_key",
+      "bank_routing_number",
+      "biometric_identifier",
+      "blood_type",
+      "certificate_license_number",
+      "city",
+      "company_name",
+      "coordinate",
+      "country",
+      "county",
+      "credit_debit_card",
+      "customer_id",
+      "cvv",
+      "date",
+      "date_of_birth",
+      "date_time",
+      "device_identifier",
+      "education_level",
+      "email",
+      "employee_id",
+      "employment_status",
+      "fax_number",
+      "first_name",
+      "gender",
+      "health_plan_beneficiary_number",
+      "http_cookie",
+      "ipv4",
+      "ipv6",
+      "language",
+      "last_name",
+      "license_plate",
+      "mac_address",
+      "medical_record_number",
+      "national_id",
+      "occupation",
+      "password",
+      "phone_number",
+      "pin",
+      "political_view",
+      "postcode",
+      "race_ethnicity",
+      "religious_belief",
+      "sexuality",
+      "ssn",
+      "state",
+      "street_address",
+      "swift_bic",
+      "tax_id",
+      "time",
+      "unique_id",
+      "url",
+      "user_name",
+      "vehicle_identifier"
+    ],
+    "ner_class_names": [
+      "O",
+      "B-account_number",
+      "I-account_number",
+      "E-account_number",
+      "S-account_number",
+      "B-age",
+      "I-age",
+      "E-age",
+      "S-age",
+      "B-api_key",
+      "I-api_key",
+      "E-api_key",
+      "S-api_key",
+      "B-bank_routing_number",
+      "I-bank_routing_number",
+      "E-bank_routing_number",
+      "S-bank_routing_number",
+      "B-biometric_identifier",
+      "I-biometric_identifier",
+      "E-biometric_identifier",
+      "S-biometric_identifier",
+      "B-blood_type",
+      "I-blood_type",
+      "E-blood_type",
+      "S-blood_type",
+      "B-certificate_license_number",
+      "I-certificate_license_number",
+      "E-certificate_license_number",
+      "S-certificate_license_number",
+      "B-city",
+      "I-city",
+      "E-city",
+      "S-city",
+      "B-company_name",
+      "I-company_name",
+      "E-company_name",
+      "S-company_name",
+      "B-coordinate",
+      "I-coordinate",
+      "E-coordinate",
+      "S-coordinate",
+      "B-country",
+      "I-country",
+      "E-country",
+      "S-country",
+      "B-county",
+      "I-county",
+      "E-county",
+      "S-county",
+      "B-credit_debit_card",
+      "I-credit_debit_card",
+      "E-credit_debit_card",
+      "S-credit_debit_card",
+      "B-customer_id",
+      "I-customer_id",
+      "E-customer_id",
+      "S-customer_id",
+      "B-cvv",
+      "I-cvv",
+      "E-cvv",
+      "S-cvv",
+      "B-date",
+      "I-date",
+      "E-date",
+      "S-date",
+      "B-date_of_birth",
+      "I-date_of_birth",
+      "E-date_of_birth",
+      "S-date_of_birth",
+      "B-date_time",
+      "I-date_time",
+      "E-date_time",
+      "S-date_time",
+      "B-device_identifier",
+      "I-device_identifier",
+      "E-device_identifier",
+      "S-device_identifier",
+      "B-education_level",
+      "I-education_level",
+      "E-education_level",
+      "S-education_level",
+      "B-email",
+      "I-email",
+      "E-email",
+      "S-email",
+      "B-employee_id",
+      "I-employee_id",
+      "E-employee_id",
+      "S-employee_id",
+      "B-employment_status",
+      "I-employment_status",
+      "E-employment_status",
+      "S-employment_status",
+      "B-fax_number",
+      "I-fax_number",
+      "E-fax_number",
+      "S-fax_number",
+      "B-first_name",
+      "I-first_name",
+      "E-first_name",
+      "S-first_name",
+      "B-gender",
+      "I-gender",
+      "E-gender",
+      "S-gender",
+      "B-health_plan_beneficiary_number",
+      "I-health_plan_beneficiary_number",
+      "E-health_plan_beneficiary_number",
+      "S-health_plan_beneficiary_number",
+      "B-http_cookie",
+      "I-http_cookie",
+      "E-http_cookie",
+      "S-http_cookie",
+      "B-ipv4",
+      "I-ipv4",
+      "E-ipv4",
+      "S-ipv4",
+      "B-ipv6",
+      "I-ipv6",
+      "E-ipv6",
+      "S-ipv6",
+      "B-language",
+      "I-language",
+      "E-language",
+      "S-language",
+      "B-last_name",
+      "I-last_name",
+      "E-last_name",
+      "S-last_name",
+      "B-license_plate",
+      "I-license_plate",
+      "E-license_plate",
+      "S-license_plate",
+      "B-mac_address",
+      "I-mac_address",
+      "E-mac_address",
+      "S-mac_address",
+      "B-medical_record_number",
+      "I-medical_record_number",
+      "E-medical_record_number",
+      "S-medical_record_number",
+      "B-national_id",
+      "I-national_id",
+      "E-national_id",
+      "S-national_id",
+      "B-occupation",
+      "I-occupation",
+      "E-occupation",
+      "S-occupation",
+      "B-password",
+      "I-password",
+      "E-password",
+      "S-password",
+      "B-phone_number",
+      "I-phone_number",
+      "E-phone_number",
+      "S-phone_number",
+      "B-pin",
+      "I-pin",
+      "E-pin",
+      "S-pin",
+      "B-political_view",
+      "I-political_view",
+      "E-political_view",
+      "S-political_view",
+      "B-postcode",
+      "I-postcode",
+      "E-postcode",
+      "S-postcode",
+      "B-race_ethnicity",
+      "I-race_ethnicity",
+      "E-race_ethnicity",
+      "S-race_ethnicity",
+      "B-religious_belief",
+      "I-religious_belief",
+      "E-religious_belief",
+      "S-religious_belief",
+      "B-sexuality",
+      "I-sexuality",
+      "E-sexuality",
+      "S-sexuality",
+      "B-ssn",
+      "I-ssn",
+      "E-ssn",
+      "S-ssn",
+      "B-state",
+      "I-state",
+      "E-state",
+      "S-state",
+      "B-street_address",
+      "I-street_address",
+      "E-street_address",
+      "S-street_address",
+      "B-swift_bic",
+      "I-swift_bic",
+      "E-swift_bic",
+      "S-swift_bic",
+      "B-tax_id",
+      "I-tax_id",
+      "E-tax_id",
+      "S-tax_id",
+      "B-time",
+      "I-time",
+      "E-time",
+      "S-time",
+      "B-unique_id",
+      "I-unique_id",
+      "E-unique_id",
+      "S-unique_id",
+      "B-url",
+      "I-url",
+      "E-url",
+      "S-url",
+      "B-user_name",
+      "I-user_name",
+      "E-user_name",
+      "S-user_name",
+      "B-vehicle_identifier",
+      "I-vehicle_identifier",
+      "E-vehicle_identifier",
+      "S-vehicle_identifier"
+    ],
+    "inference_contract_version": 1
+  },
+  "classifier_bias": true,
+  "_name_or_path": "OpenMed/privacy-filter-nemotron",
+  "_mlx_task": "token-classification",
+  "_mlx_family": "openai-privacy-filter",
+  "_mlx_model_type": "openai-privacy-filter",
+  "_mlx_runtime": {
+    "experimental": true,
+    "decode": "bioes-viterbi",
+    "tokenizer": "tiktoken"
+  },
+  "num_experts": 128,
+  "experts_per_token": 4,
+  "_mlx_viterbi_biases": {},
+  "rope_theta": 150000.0,
+  "rope_scaling_factor": 32.0,
+  "rope_ntk_alpha": 1.0,
+  "rope_ntk_beta": 32.0,
+  "encoding": "o200k_base",
+  "bidirectional_context": true,
+  "bidirectional_left_context": 64,
+  "bidirectional_right_context": 63,
+  "hidden_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0.0,
+  "layer_norm_eps": 1e-12,
+  "swiglu_limit": 7.0,
+  "_mlx_weights_format": "safetensors"
+}

id2label.json

@@ -0,0 +1,223 @@
+{
+  "0": "O",
+  "1": "B-account_number",
+  "2": "I-account_number",
+  "3": "E-account_number",
+  "4": "S-account_number",
+  "5": "B-age",
+  "6": "I-age",
+  "7": "E-age",
+  "8": "S-age",
+  "9": "B-api_key",
+  "10": "I-api_key",
+  "11": "E-api_key",
+  "12": "S-api_key",
+  "13": "B-bank_routing_number",
+  "14": "I-bank_routing_number",
+  "15": "E-bank_routing_number",
+  "16": "S-bank_routing_number",
+  "17": "B-biometric_identifier",
+  "18": "I-biometric_identifier",
+  "19": "E-biometric_identifier",
+  "20": "S-biometric_identifier",
+  "21": "B-blood_type",
+  "22": "I-blood_type",
+  "23": "E-blood_type",
+  "24": "S-blood_type",
+  "25": "B-certificate_license_number",
+  "26": "I-certificate_license_number",
+  "27": "E-certificate_license_number",
+  "28": "S-certificate_license_number",
+  "29": "B-city",
+  "30": "I-city",
+  "31": "E-city",
+  "32": "S-city",
+  "33": "B-company_name",
+  "34": "I-company_name",
+  "35": "E-company_name",
+  "36": "S-company_name",
+  "37": "B-coordinate",
+  "38": "I-coordinate",
+  "39": "E-coordinate",
+  "40": "S-coordinate",
+  "41": "B-country",
+  "42": "I-country",
+  "43": "E-country",
+  "44": "S-country",
+  "45": "B-county",
+  "46": "I-county",
+  "47": "E-county",
+  "48": "S-county",
+  "49": "B-credit_debit_card",
+  "50": "I-credit_debit_card",
+  "51": "E-credit_debit_card",
+  "52": "S-credit_debit_card",
+  "53": "B-customer_id",
+  "54": "I-customer_id",
+  "55": "E-customer_id",
+  "56": "S-customer_id",
+  "57": "B-cvv",
+  "58": "I-cvv",
+  "59": "E-cvv",
+  "60": "S-cvv",
+  "61": "B-date",
+  "62": "I-date",
+  "63": "E-date",
+  "64": "S-date",
+  "65": "B-date_of_birth",
+  "66": "I-date_of_birth",
+  "67": "E-date_of_birth",
+  "68": "S-date_of_birth",
+  "69": "B-date_time",
+  "70": "I-date_time",
+  "71": "E-date_time",
+  "72": "S-date_time",
+  "73": "B-device_identifier",
+  "74": "I-device_identifier",
+  "75": "E-device_identifier",
+  "76": "S-device_identifier",
+  "77": "B-education_level",
+  "78": "I-education_level",
+  "79": "E-education_level",
+  "80": "S-education_level",
+  "81": "B-email",
+  "82": "I-email",
+  "83": "E-email",
+  "84": "S-email",
+  "85": "B-employee_id",
+  "86": "I-employee_id",
+  "87": "E-employee_id",
+  "88": "S-employee_id",
+  "89": "B-employment_status",
+  "90": "I-employment_status",
+  "91": "E-employment_status",
+  "92": "S-employment_status",
+  "93": "B-fax_number",
+  "94": "I-fax_number",
+  "95": "E-fax_number",
+  "96": "S-fax_number",
+  "97": "B-first_name",
+  "98": "I-first_name",
+  "99": "E-first_name",
+  "100": "S-first_name",
+  "101": "B-gender",
+  "102": "I-gender",
+  "103": "E-gender",
+  "104": "S-gender",
+  "105": "B-health_plan_beneficiary_number",
+  "106": "I-health_plan_beneficiary_number",
+  "107": "E-health_plan_beneficiary_number",
+  "108": "S-health_plan_beneficiary_number",
+  "109": "B-http_cookie",
+  "110": "I-http_cookie",
+  "111": "E-http_cookie",
+  "112": "S-http_cookie",
+  "113": "B-ipv4",
+  "114": "I-ipv4",
+  "115": "E-ipv4",
+  "116": "S-ipv4",
+  "117": "B-ipv6",
+  "118": "I-ipv6",
+  "119": "E-ipv6",
+  "120": "S-ipv6",
+  "121": "B-language",
+  "122": "I-language",
+  "123": "E-language",
+  "124": "S-language",
+  "125": "B-last_name",
+  "126": "I-last_name",
+  "127": "E-last_name",
+  "128": "S-last_name",
+  "129": "B-license_plate",
+  "130": "I-license_plate",
+  "131": "E-license_plate",
+  "132": "S-license_plate",
+  "133": "B-mac_address",
+  "134": "I-mac_address",
+  "135": "E-mac_address",
+  "136": "S-mac_address",
+  "137": "B-medical_record_number",
+  "138": "I-medical_record_number",
+  "139": "E-medical_record_number",
+  "140": "S-medical_record_number",
+  "141": "B-national_id",
+  "142": "I-national_id",
+  "143": "E-national_id",
+  "144": "S-national_id",
+  "145": "B-occupation",
+  "146": "I-occupation",
+  "147": "E-occupation",
+  "148": "S-occupation",
+  "149": "B-password",
+  "150": "I-password",
+  "151": "E-password",
+  "152": "S-password",
+  "153": "B-phone_number",
+  "154": "I-phone_number",
+  "155": "E-phone_number",
+  "156": "S-phone_number",
+  "157": "B-pin",
+  "158": "I-pin",
+  "159": "E-pin",
+  "160": "S-pin",
+  "161": "B-political_view",
+  "162": "I-political_view",
+  "163": "E-political_view",
+  "164": "S-political_view",
+  "165": "B-postcode",
+  "166": "I-postcode",
+  "167": "E-postcode",
+  "168": "S-postcode",
+  "169": "B-race_ethnicity",
+  "170": "I-race_ethnicity",
+  "171": "E-race_ethnicity",
+  "172": "S-race_ethnicity",
+  "173": "B-religious_belief",
+  "174": "I-religious_belief",
+  "175": "E-religious_belief",
+  "176": "S-religious_belief",
+  "177": "B-sexuality",
+  "178": "I-sexuality",
+  "179": "E-sexuality",
+  "180": "S-sexuality",
+  "181": "B-ssn",
+  "182": "I-ssn",
+  "183": "E-ssn",
+  "184": "S-ssn",
+  "185": "B-state",
+  "186": "I-state",
+  "187": "E-state",
+  "188": "S-state",
+  "189": "B-street_address",
+  "190": "I-street_address",
+  "191": "E-street_address",
+  "192": "S-street_address",
+  "193": "B-swift_bic",
+  "194": "I-swift_bic",
+  "195": "E-swift_bic",
+  "196": "S-swift_bic",
+  "197": "B-tax_id",
+  "198": "I-tax_id",
+  "199": "E-tax_id",
+  "200": "S-tax_id",
+  "201": "B-time",
+  "202": "I-time",
+  "203": "E-time",
+  "204": "S-time",
+  "205": "B-unique_id",
+  "206": "I-unique_id",
+  "207": "E-unique_id",
+  "208": "S-unique_id",
+  "209": "B-url",
+  "210": "I-url",
+  "211": "E-url",
+  "212": "S-url",
+  "213": "B-user_name",
+  "214": "I-user_name",
+  "215": "E-user_name",
+  "216": "S-user_name",
+  "217": "B-vehicle_identifier",
+  "218": "I-vehicle_identifier",
+  "219": "E-vehicle_identifier",
+  "220": "S-vehicle_identifier"
+}

openmed-mlx.json

@@ -0,0 +1,31 @@
+{
+  "format": "openmed-mlx",
+  "format_version": 2,
+  "task": "token-classification",
+  "family": "openai-privacy-filter",
+  "source_model_id": "OpenMed/privacy-filter-nemotron",
+  "config_path": "config.json",
+  "label_map_path": "id2label.json",
+  "preferred_weights": "weights.safetensors",
+  "fallback_weights": [
+    "weights.npz"
+  ],
+  "available_weights": [
+    "weights.safetensors"
+  ],
+  "weights_format": "safetensors",
+  "quantization": null,
+  "max_sequence_length": 131072,
+  "tokenizer": {
+    "path": ".",
+    "files": [
+      "tokenizer.json",
+      "tokenizer_config.json"
+    ]
+  },
+  "runtime": {
+    "experimental": true,
+    "decode": "bioes-viterbi",
+    "tokenizer": "tiktoken"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
+size 27868174

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "backend": "tokenizers",
+  "eos_token": "<|endoftext|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "TokenizersBackend"
+}

weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d081f4849fd0d3d288b4ee21459960c9348bc9f2ae0bec7a997f61723a8fb30a
+size 2799225281