Upload MLX packaging for OpenMed-NER-ProteinDetect-BioMed-109M-mlx

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+base_model: OpenMed/OpenMed-NER-ProteinDetect-BioMed-109M
+pipeline_tag: token-classification
+library_name: openmed
+tags:
+  - openmed
+  - mlx
+  - apple-silicon
+  - token-classification
+  - pii
+  - de-identification
+  - medical
+  - clinical
+---
+
+# OpenMed-NER-ProteinDetect-BioMed-109M for OpenMed MLX
+
+This repository contains an OpenMed MLX conversion of [`OpenMed/OpenMed-NER-ProteinDetect-BioMed-109M`](https://huggingface.co/OpenMed/OpenMed-NER-ProteinDetect-BioMed-109M) for Apple Silicon inference with [OpenMed](https://github.com/maziyarpanahi/openmed).
+
+Artifact metadata:
+
+- OpenMed MLX task: `token-classification`
+- OpenMed MLX family: `bert`
+- Weight format: `safetensors`
+- Runtime API: `OpenMed MLX token-classification backend`
+
+[OpenMed](https://github.com/maziyarpanahi/openmed) is the main product experience:
+
+- Install the Python package with `pip install openmed`
+- Enable Apple Silicon acceleration with `pip install "openmed[mlx]"`
+- Load this MLX model directly from the Hub or from a local snapshot
+- For Apple apps, use OpenMedKit from the same GitHub repository with a compatible CoreML bundle
+
+This MLX repo is meant to pair with:
+
+- OpenMed GitHub: [https://github.com/maziyarpanahi/openmed](https://github.com/maziyarpanahi/openmed)
+- OpenMed website: [https://openmed.life](https://openmed.life)
+- Source checkpoint: [`OpenMed/OpenMed-NER-ProteinDetect-BioMed-109M`](https://huggingface.co/OpenMed/OpenMed-NER-ProteinDetect-BioMed-109M)
+
+## Quick Start
+
+```bash
+pip install openmed
+pip install "openmed[mlx]"
+```
+
+```python
+from openmed import analyze_text
+from openmed.core.config import OpenMedConfig
+
+result = analyze_text(
+    "Patient John Doe, DOB 1990-05-15, SSN 123-45-6789",
+    model_name="OpenMed/OpenMed-NER-ProteinDetect-BioMed-109M",
+    config=OpenMedConfig(backend="mlx"),
+)
+
+for entity in result.entities:
+    print(entity.label, entity.text, round(entity.confidence, 4))
+```
+
+## Swift and Apple Apps
+
+Use Swift with OpenMedKit, not with MLX weight files directly.
+
+1. Open Xcode and go to File > Add Package Dependencies.
+2. Paste the OpenMed repository URL: `https://github.com/maziyarpanahi/openmed`
+3. Choose the package product OpenMedKit from the repository.
+4. Add a compatible CoreML model bundle plus `id2label.json` to your app target.
+
+This MLX model is for Python services on Apple Silicon, local MLX inference on macOS, and Hub-hosted model distribution. If a given environment cannot write `weights.safetensors`, OpenMed falls back to `weights.npz` so the model remains usable.
+
+## Credits
+
+- Base checkpoint: [`OpenMed/OpenMed-NER-ProteinDetect-BioMed-109M`](https://huggingface.co/OpenMed/OpenMed-NER-ProteinDetect-BioMed-109M)
+- OpenMed GitHub: [https://github.com/maziyarpanahi/openmed](https://github.com/maziyarpanahi/openmed)
+- OpenMed website: [https://openmed.life](https://openmed.life)
+- MLX conversion and runtime support: OpenMed
+- Swift runtime for Apple apps: OpenMedKit from the OpenMed repository

config.json

@@ -0,0 +1,68 @@
+{
+  "transformers_version": "5.5.0",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "output_hidden_states": false,
+  "return_dict": true,
+  "dtype": "bfloat16",
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "id2label": {
+    "0": "B-protein",
+    "1": "B-protein_complex",
+    "2": "B-protein_enum",
+    "3": "B-protein_familiy_or_group",
+    "4": "B-protein_variant",
+    "5": "I-protein",
+    "6": "I-protein_complex",
+    "7": "I-protein_enum",
+    "8": "I-protein_familiy_or_group",
+    "9": "I-protein_variant",
+    "10": "O"
+  },
+  "label2id": {
+    "B-protein": 0,
+    "B-protein_complex": 1,
+    "B-protein_enum": 2,
+    "B-protein_familiy_or_group": 3,
+    "B-protein_variant": 4,
+    "I-protein": 5,
+    "I-protein_complex": 6,
+    "I-protein_enum": 7,
+    "I-protein_familiy_or_group": 8,
+    "I-protein_variant": 9,
+    "O": 10
+  },
+  "problem_type": null,
+  "vocab_size": 30522,
+  "hidden_size": 768,
+  "num_hidden_layers": 12,
+  "num_attention_heads": 12,
+  "intermediate_size": 3072,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "attention_probs_dropout_prob": 0.2,
+  "max_position_embeddings": 512,
+  "type_vocab_size": 2,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-07,
+  "pad_token_id": 0,
+  "use_cache": true,
+  "classifier_dropout": 0.2,
+  "is_decoder": false,
+  "add_cross_attention": false,
+  "bos_token_id": null,
+  "eos_token_id": null,
+  "tie_word_embeddings": true,
+  "_name_or_path": "OpenMed/OpenMed-NER-ProteinDetect-BioMed-109M",
+  "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": 11,
+  "_mlx_weights_format": "safetensors"
+}

id2label.json

@@ -0,0 +1,13 @@
+{
+  "0": "B-protein",
+  "1": "B-protein_complex",
+  "2": "B-protein_enum",
+  "3": "B-protein_familiy_or_group",
+  "4": "B-protein_variant",
+  "5": "I-protein",
+  "6": "I-protein_complex",
+  "7": "I-protein_enum",
+  "8": "I-protein_familiy_or_group",
+  "9": "I-protein_variant",
+  "10": "O"
+}

openmed-mlx.json

@@ -0,0 +1,26 @@
+{
+  "format": "openmed-mlx",
+  "format_version": 2,
+  "task": "token-classification",
+  "family": "bert",
+  "source_model_id": "OpenMed/OpenMed-NER-ProteinDetect-BioMed-109M",
+  "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 +1,24 @@
+{
+  "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": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "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 sha256:64a8942b3ca375e810dd4e7e31ca5b7e7fa9baa3e948cf0f70ec537d8f421dd2
+size 435621544