Upload MLX packaging for OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1-mlx

README.md

@@ -0,0 +1,106 @@
+---
+license: apache-2.0
+base_model: OpenMed/OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1
+pipeline_tag: token-classification
+library_name: openmed
+tags:
+  - openmed
+  - mlx
+  - apple-silicon
+  - token-classification
+  - pii
+  - de-identification
+  - medical
+  - clinical
+  - bert
+---
+
+# OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1 for OpenMed MLX
+
+This repository contains an MLX packaging of [`OpenMed/OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1`](https://huggingface.co/OpenMed/OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1) for Apple Silicon inference with [OpenMed](https://github.com/maziyarpanahi/openmed).
+
+## At a Glance
+
+- Source checkpoint: [`OpenMed/OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1`](https://huggingface.co/OpenMed/OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1)
+- Model family: `bert` (`BertForTokenClassification`)
+- Primary language hint: Portuguese (`pt`)
+- Artifact layout: legacy-compatible MLX (`config.json`, `id2label.json`, MLX weight files)
+- Weight format: `safetensors`
+- Python MLX: supported through `openmed[mlx]` on Apple Silicon Macs
+
+## Python Quick Start
+
+Use the standard OpenMed API if you want OpenMed to choose the right runtime automatically:
+
+```bash
+pip install "openmed[mlx]"
+```
+
+```python
+from openmed import extract_pii
+
+text = "<your clinical note here>"
+result = extract_pii(
+    text,
+    model_name="OpenMed/OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1",
+    use_smart_merging=True,
+)
+
+for entity in result.entities:
+    print(entity.label, entity.text, round(entity.confidence, 4))
+```
+
+On Apple Silicon, OpenMed can use this preconverted MLX artifact when `openmed[mlx]` is installed. On other systems, OpenMed falls back to the Hugging Face / PyTorch backend.
+
+## Use This Preconverted MLX Repo Directly
+
+If you want to use this MLX snapshot explicitly, download it locally and point OpenMed at the directory:
+
+```bash
+pip install "openmed[mlx]"
+hf download OpenMed/OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1-mlx --local-dir ./OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1-mlx
+```
+
+If this repo is private in your environment, authenticate first with `hf auth login` or set `HF_TOKEN`.
+
+```python
+from openmed import extract_pii
+from openmed.core import OpenMedConfig
+
+text = "<your clinical note here>"
+result = extract_pii(
+    text,
+    model_name="./OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1-mlx",
+    config=OpenMedConfig(backend="mlx"),
+    use_smart_merging=True,
+)
+
+print(result.entities)
+```
+
+## Swift Status
+
+This repo is based on `bert`. Python MLX supports this artifact today, and this family is in the current OpenMedKit Swift MLX support matrix.
+
+If you are building an Apple app today, the recommended paths for this model are:
+
+- Python MLX for evaluation or local workflows on Apple Silicon
+- CoreML in OpenMedKit if you already have a compatible bundled Apple export
+- Track the current Swift support matrix in the [OpenMedKit docs](https://openmed.life/docs/swift-openmedkit/)
+
+## Artifact Notes
+
+This repo uses the current legacy-compatible MLX layout:
+
+- `config.json`
+- `id2label.json`
+- MLX weight files (`weights.safetensors` and/or `weights.npz`)
+
+Tokenizer assets are bundled in this repo.
+
+## Links
+
+- Source checkpoint: [`OpenMed/OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1`](https://huggingface.co/OpenMed/OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1)
+- OpenMed GitHub: [https://github.com/maziyarpanahi/openmed](https://github.com/maziyarpanahi/openmed)
+- MLX backend docs: [https://openmed.life/docs/mlx-backend/](https://openmed.life/docs/mlx-backend/)
+- OpenMedKit docs: [https://openmed.life/docs/swift-openmedkit/](https://openmed.life/docs/swift-openmedkit/)

config.json

@@ -0,0 +1,199 @@
+{
+  "transformers_version": "5.5.0",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "output_hidden_states": false,
+  "return_dict": true,
+  "dtype": "float32",
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "id2label": {
+    "0": "O",
+    "1": "B-ACCOUNTNAME",
+    "2": "B-AGE",
+    "3": "B-AMOUNT",
+    "4": "B-BANKACCOUNT",
+    "5": "B-BIC",
+    "6": "B-BITCOINADDRESS",
+    "7": "B-BUILDINGNUMBER",
+    "8": "B-CITY",
+    "9": "B-COUNTY",
+    "10": "B-CREDITCARD",
+    "11": "B-CREDITCARDISSUER",
+    "12": "B-CURRENCY",
+    "13": "B-CURRENCYCODE",
+    "14": "B-CURRENCYNAME",
+    "15": "B-CURRENCYSYMBOL",
+    "16": "B-CVV",
+    "17": "B-DATE",
+    "18": "B-DATEOFBIRTH",
+    "19": "B-EMAIL",
+    "20": "B-ETHEREUMADDRESS",
+    "21": "B-EYECOLOR",
+    "22": "B-FIRSTNAME",
+    "23": "B-GENDER",
+    "24": "B-GPSCOORDINATES",
+    "25": "B-HEIGHT",
+    "26": "B-IBAN",
+    "27": "B-IMEI",
+    "28": "B-IPADDRESS",
+    "29": "B-JOBDEPARTMENT",
+    "30": "B-JOBTITLE",
+    "31": "B-LASTNAME",
+    "32": "B-LITECOINADDRESS",
+    "33": "B-MACADDRESS",
+    "34": "B-MASKEDNUMBER",
+    "35": "B-MIDDLENAME",
+    "36": "B-OCCUPATION",
+    "37": "B-ORDINALDIRECTION",
+    "38": "B-ORGANIZATION",
+    "39": "B-PASSWORD",
+    "40": "B-PHONE",
+    "41": "B-PIN",
+    "42": "B-PREFIX",
+    "43": "B-SECONDARYADDRESS",
+    "44": "B-SEX",
+    "45": "B-SSN",
+    "46": "B-STATE",
+    "47": "B-STREET",
+    "48": "B-TIME",
+    "49": "B-URL",
+    "50": "B-USERAGENT",
+    "51": "B-USERNAME",
+    "52": "B-VIN",
+    "53": "B-VRM",
+    "54": "B-ZIPCODE",
+    "55": "I-ACCOUNTNAME",
+    "56": "I-AGE",
+    "57": "I-AMOUNT",
+    "58": "I-CITY",
+    "59": "I-COUNTY",
+    "60": "I-CURRENCY",
+    "61": "I-CURRENCYNAME",
+    "62": "I-DATE",
+    "63": "I-DATEOFBIRTH",
+    "64": "I-EYECOLOR",
+    "65": "I-GENDER",
+    "66": "I-HEIGHT",
+    "67": "I-JOBTITLE",
+    "68": "I-ORGANIZATION",
+    "69": "I-PHONE",
+    "70": "I-SECONDARYADDRESS",
+    "71": "I-SSN",
+    "72": "I-STATE",
+    "73": "I-STREET",
+    "74": "I-TIME",
+    "75": "I-USERAGENT"
+  },
+  "label2id": {
+    "B-ACCOUNTNAME": 1,
+    "B-AGE": 2,
+    "B-AMOUNT": 3,
+    "B-BANKACCOUNT": 4,
+    "B-BIC": 5,
+    "B-BITCOINADDRESS": 6,
+    "B-BUILDINGNUMBER": 7,
+    "B-CITY": 8,
+    "B-COUNTY": 9,
+    "B-CREDITCARD": 10,
+    "B-CREDITCARDISSUER": 11,
+    "B-CURRENCY": 12,
+    "B-CURRENCYCODE": 13,
+    "B-CURRENCYNAME": 14,
+    "B-CURRENCYSYMBOL": 15,
+    "B-CVV": 16,
+    "B-DATE": 17,
+    "B-DATEOFBIRTH": 18,
+    "B-EMAIL": 19,
+    "B-ETHEREUMADDRESS": 20,
+    "B-EYECOLOR": 21,
+    "B-FIRSTNAME": 22,
+    "B-GENDER": 23,
+    "B-GPSCOORDINATES": 24,
+    "B-HEIGHT": 25,
+    "B-IBAN": 26,
+    "B-IMEI": 27,
+    "B-IPADDRESS": 28,
+    "B-JOBDEPARTMENT": 29,
+    "B-JOBTITLE": 30,
+    "B-LASTNAME": 31,
+    "B-LITECOINADDRESS": 32,
+    "B-MACADDRESS": 33,
+    "B-MASKEDNUMBER": 34,
+    "B-MIDDLENAME": 35,
+    "B-OCCUPATION": 36,
+    "B-ORDINALDIRECTION": 37,
+    "B-ORGANIZATION": 38,
+    "B-PASSWORD": 39,
+    "B-PHONE": 40,
+    "B-PIN": 41,
+    "B-PREFIX": 42,
+    "B-SECONDARYADDRESS": 43,
+    "B-SEX": 44,
+    "B-SSN": 45,
+    "B-STATE": 46,
+    "B-STREET": 47,
+    "B-TIME": 48,
+    "B-URL": 49,
+    "B-USERAGENT": 50,
+    "B-USERNAME": 51,
+    "B-VIN": 52,
+    "B-VRM": 53,
+    "B-ZIPCODE": 54,
+    "I-ACCOUNTNAME": 55,
+    "I-AGE": 56,
+    "I-AMOUNT": 57,
+    "I-CITY": 58,
+    "I-COUNTY": 59,
+    "I-CURRENCY": 60,
+    "I-CURRENCYNAME": 61,
+    "I-DATE": 62,
+    "I-DATEOFBIRTH": 63,
+    "I-EYECOLOR": 64,
+    "I-GENDER": 65,
+    "I-HEIGHT": 66,
+    "I-JOBTITLE": 67,
+    "I-ORGANIZATION": 68,
+    "I-PHONE": 69,
+    "I-SECONDARYADDRESS": 70,
+    "I-SSN": 71,
+    "I-STATE": 72,
+    "I-STREET": 73,
+    "I-TIME": 74,
+    "I-USERAGENT": 75,
+    "O": 0
+  },
+  "problem_type": null,
+  "vocab_size": 30522,
+  "hidden_size": 1024,
+  "num_hidden_layers": 24,
+  "num_attention_heads": 16,
+  "intermediate_size": 4096,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0.1,
+  "max_position_embeddings": 512,
+  "type_vocab_size": 2,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-12,
+  "pad_token_id": 0,
+  "use_cache": false,
+  "classifier_dropout": null,
+  "is_decoder": false,
+  "add_cross_attention": false,
+  "bos_token_id": null,
+  "eos_token_id": null,
+  "tie_word_embeddings": true,
+  "_name_or_path": "OpenMed/OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1",
+  "gradient_checkpointing": false,
+  "model_type": "bert",
+  "position_embedding_type": "absolute",
+  "output_attentions": false,
+  "_mlx_task": "token-classification",
+  "_mlx_family": "bert",
+  "_mlx_position_offset": 0,
+  "_mlx_model_type": "bert",
+  "num_labels": 76,
+  "_mlx_weights_format": "safetensors"
+}

id2label.json

@@ -0,0 +1,78 @@
+{
+  "0": "O",
+  "1": "B-ACCOUNTNAME",
+  "2": "B-AGE",
+  "3": "B-AMOUNT",
+  "4": "B-BANKACCOUNT",
+  "5": "B-BIC",
+  "6": "B-BITCOINADDRESS",
+  "7": "B-BUILDINGNUMBER",
+  "8": "B-CITY",
+  "9": "B-COUNTY",
+  "10": "B-CREDITCARD",
+  "11": "B-CREDITCARDISSUER",
+  "12": "B-CURRENCY",
+  "13": "B-CURRENCYCODE",
+  "14": "B-CURRENCYNAME",
+  "15": "B-CURRENCYSYMBOL",
+  "16": "B-CVV",
+  "17": "B-DATE",
+  "18": "B-DATEOFBIRTH",
+  "19": "B-EMAIL",
+  "20": "B-ETHEREUMADDRESS",
+  "21": "B-EYECOLOR",
+  "22": "B-FIRSTNAME",
+  "23": "B-GENDER",
+  "24": "B-GPSCOORDINATES",
+  "25": "B-HEIGHT",
+  "26": "B-IBAN",
+  "27": "B-IMEI",
+  "28": "B-IPADDRESS",
+  "29": "B-JOBDEPARTMENT",
+  "30": "B-JOBTITLE",
+  "31": "B-LASTNAME",
+  "32": "B-LITECOINADDRESS",
+  "33": "B-MACADDRESS",
+  "34": "B-MASKEDNUMBER",
+  "35": "B-MIDDLENAME",
+  "36": "B-OCCUPATION",
+  "37": "B-ORDINALDIRECTION",
+  "38": "B-ORGANIZATION",
+  "39": "B-PASSWORD",
+  "40": "B-PHONE",
+  "41": "B-PIN",
+  "42": "B-PREFIX",
+  "43": "B-SECONDARYADDRESS",
+  "44": "B-SEX",
+  "45": "B-SSN",
+  "46": "B-STATE",
+  "47": "B-STREET",
+  "48": "B-TIME",
+  "49": "B-URL",
+  "50": "B-USERAGENT",
+  "51": "B-USERNAME",
+  "52": "B-VIN",
+  "53": "B-VRM",
+  "54": "B-ZIPCODE",
+  "55": "I-ACCOUNTNAME",
+  "56": "I-AGE",
+  "57": "I-AMOUNT",
+  "58": "I-CITY",
+  "59": "I-COUNTY",
+  "60": "I-CURRENCY",
+  "61": "I-CURRENCYNAME",
+  "62": "I-DATE",
+  "63": "I-DATEOFBIRTH",
+  "64": "I-EYECOLOR",
+  "65": "I-GENDER",
+  "66": "I-HEIGHT",
+  "67": "I-JOBTITLE",
+  "68": "I-ORGANIZATION",
+  "69": "I-PHONE",
+  "70": "I-SECONDARYADDRESS",
+  "71": "I-SSN",
+  "72": "I-STATE",
+  "73": "I-STREET",
+  "74": "I-TIME",
+  "75": "I-USERAGENT"
+}

openmed-mlx.json

@@ -0,0 +1,26 @@
+{
+  "format": "openmed-mlx",
+  "format_version": 2,
+  "task": "token-classification",
+  "family": "bert",
+  "source_model_id": "OpenMed/OpenMed-PII-Portuguese-ClinicalBGE-Large-335M-v1",
+  "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": 512,
+  "tokenizer": {
+    "path": ".",
+    "files": [
+      "tokenizer.json",
+      "tokenizer_config.json"
+    ]
+  }
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93afe8ca6f8361c79ae3f3b5ff745736433549ade6d0a7c8b19f4fa86670165
+size 1336723265