Refresh OpenMed cross-platform model card

README.md

@@ -1,70 +1,162 @@
 ---
+library_name: openmed
 license: apache-2.0
+language:
+- en
 pipeline_tag: token-classification
-library_name: openmed
+base_model: OpenMed/OpenMed-NER-ProteinDetect-SnowMed-568M
 tags:
 - openmed
+- onnx
 - medical-nlp
+- medical-ner
+- android
+- webassembly
+- webgpu
 ---
 
-# OpenMed-NER-ProteinDetect-SnowMed-568M-v1-onnx-android
+<div align="center">
+<img src="https://raw.githubusercontent.com/maziyarpanahi/openmed/master/docs/brand/openmed-mascot-lockup.png" alt="OpenMed: on-device clinical AI" width="360">
+
+# OpenMed Protein NER 568M
+
+`OpenMed/OpenMed-NER-ProteinDetect-SnowMed-568M-v1-onnx-android`
+
+**A 568M XLM-RoBERTa model for extracting protein mentions in English clinical and biomedical text.**  
+Runs locally after download on Python CPU, in the browser, and on Android.
+
+[OpenMed](https://github.com/maziyarpanahi/openmed) | [Documentation](https://openmed.life/docs) | [Model collection](https://huggingface.co/OpenMed) | [Paper](https://arxiv.org/abs/2508.01630)
+</div>
 
-This model card is rendered from the OpenMed model manifest. Update `models.jsonl` and rerun the publish step instead of editing this file directly.
+## Model
+
+| Field | Value |
+|---|---|
+| Task | Protein named-entity recognition |
+| Language | English |
+| Architecture | XLM-RoBERTa |
+| Parameters | 568M (568,000,000) |
+| Maximum sequence length | 512 tokens |
+| Entity labels | `protein`, `protein_complex`, `protein_enum`, `protein_familiy_or_group`, `protein_variant` |
+| Source model | [`OpenMed/OpenMed-NER-ProteinDetect-SnowMed-568M`](https://huggingface.co/OpenMed/OpenMed-NER-ProteinDetect-SnowMed-568M) |
+| License | apache-2.0 |
 
 ## OpenMed in Python on CPU
 
+```bash
+pip install "openmed[onnx-runtime]>=1.8.2"
+```
+
 ```python
 from openmed import OnnxModel
+
 model = OnnxModel.from_pretrained("OpenMed/OpenMed-NER-ProteinDetect-SnowMed-568M-v1-onnx-android")
-entities = model("Patient Alice Nguyen was seen in cardiology.")
+entities = model("HER2 expression was elevated in the tumor.")
+
+for entity in entities:
+    print(entity.to_dict())
 ```
 
+OpenMed selects the CPU-oriented INT8 graph by default and returns labels, confidence scores, exact character offsets, and source text.
+
 ## OpenMed in Web
 
+```bash
+npm install @openmed/openmedkit-web @huggingface/transformers onnxruntime-web
+```
+
 ```typescript
 import { loadOnnxModel } from "@openmed/openmedkit-web";
-const model = await loadOnnxModel("OpenMed/OpenMed-NER-ProteinDetect-SnowMed-568M-v1-onnx-android");
-const entities = await model("Patient Alice Nguyen was seen in cardiology.");
+
+const repo = "OpenMed/OpenMed-NER-ProteinDetect-SnowMed-568M-v1-onnx-android";
+const model = await loadOnnxModel(repo);
+const entities = await model("HER2 expression was elevated in the tumor.");
+```
+
+The default INT8 path runs with WebAssembly. For WebGPU, select the FP16 graph:
+
+```typescript
+const model = await loadOnnxModel(repo, {
+  variant: "fp16",
+  device: "webgpu",
+});
 ```
 
 ## OpenMedKit for Android
 
+Add JitPack to the consumer application's `settings.gradle.kts`:
+
 ```kotlin
-val model = OpenMedKit.fromDirectory(modelDirectory)
-val entities = model.analyzeText("Patient Alice Nguyen was seen in cardiology.")
+dependencyResolutionManagement {
+    repositories {
+        google()
+        mavenCentral()
+        maven {
+            url = uri("https://jitpack.io")
+            content { includeGroup("com.github.maziyarpanahi") }
+        }
+    }
+}
 ```
 
-## Manifest Summary
+Use the matching OpenMed GitHub release tag:
 
-| Field | Value |
-|---|---|
-| Repository | `OpenMed/OpenMed-NER-ProteinDetect-SnowMed-568M-v1-onnx-android` |
-| Family | NER |
-| Task | token-classification |
-| Languages | en |
-| Tier | Not specified |
-| Parameters | 568M (568,000,000) |
-| Architecture | xlm-roberta |
-| Base model | OpenMed/OpenMed-NER-ProteinDetect-SnowMed-568M |
-| Formats | onnx-android, int8 |
-| License | apache-2.0 |
-| arXiv | [arXiv:2508.01630](https://arxiv.org/abs/2508.01630) |
-| Reproducibility hash | `sha256:52980c11e54355be05351d881b8e8fd8f2ef8f99d2d2ebc0f5ee7cb86e67ee68` |
-| Released | 2026-07-12 |
+```kotlin
+dependencies {
+    implementation("com.github.maziyarpanahi:openmed:v1.8.2")
+}
+```
 
-## Benchmark
+After downloading this model repository into an app-controlled directory:
 
-| Dataset | Micro F1 | Recall |
-|---|---:|---:|
-| Not reported | Not reported | Not reported |
+```kotlin
+import com.openmed.openmedkit.OpenMedKit
 
-## Canonical Labels
+OpenMedKit.fromDirectory(modelDirectory).use { model ->
+    val entities = model.analyzeText("HER2 expression was elevated in the tumor.")
+}
+```
 
-`protein`, `protein_complex`, `protein_enum`, `protein_familiy_or_group`, `protein_variant`
+Inference and tokenization remain on-device.
 
-## Artifact Format
+## Included Artifacts
 
-| Field | Value |
+| Artifact | Recommended use |
 |---|---|
-| Runtime artifacts | onnx-android |
-| Quantization | int8 |
+| `model_int8.onnx` | CPU, WebAssembly, and Android default |
+| `model_fp16.onnx` | WebGPU and compatible accelerated runtimes |
+| `model.onnx` | Full-precision reference |
+| `tokenizer.json` | Cross-platform tokenizer |
+| `openmed-onnx.json` | Runtime contract and operator metadata |
+
+All graphs use opset 18, dynamic batch and sequence axes, stable tensor names, and source-text offset metadata.
+
+## The OpenMed Ecosystem
+
+This model is part of **OpenMed**, an Apache-2.0, local-first clinical AI stack:
+
+- **1,500+ medical models** for clinical NER, biomedical extraction, and privacy.
+- **PII detection and de-identification** across 55+ identifier types and 17 languages.
+- **Python, MLX, Swift, Android, React Native, Web, REST, and gRPC** runtimes.
+- **Structured and multimodal intake** for OCR, documents, DICOM, FHIR, and HL7.
+- **Offline and air-gapped deployment** with no telemetry by default.
+
+## Intended Use and Limitations
+
+This model is intended for extracting protein mentions. It does not diagnose conditions or make clinical decisions. Evaluate recall, thresholds, and span behavior on appropriately governed data before deployment. Local execution supports privacy-preserving workflows but does not by itself guarantee regulatory compliance.
+
+All examples in this card are synthetic.
+
+## Citation
+
+```bibtex
+@misc{panahi2025openmedneropensourcedomainadapted,
+  title={OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art
+         Transformers for Biomedical NER Across 12 Public Datasets},
+  author={Maziyar Panahi},
+  year={2025},
+  eprint={2508.01630},
+  archivePrefix={arXiv},
+  primaryClass={cs.CL}
+}
+```