Hugging Face's logo

OpenMed
/
OpenMed-ZeroShot-NER-Pharma-Small-166M-mlx

Token Classification
MLX
GLiNER
English
openmed
deberta-v2
apple-silicon
zero-shot-ner
medical
clinical
Model card Files
xet
 Community
OpenMed-ZeroShot-NER-Pharma-Small-166M-mlx / README.md
MaziyarPanahi's picture
MaziyarPanahi
Upload MLX packaging for OpenMed-ZeroShot-NER-Pharma-Small-166M-mlx
a567fad verified
preview code
|
Raw
History Blame
3.27 kB
metadata 
license: apache-2.0
base_model: OpenMed/OpenMed-ZeroShot-NER-Pharma-Small-166M
pipeline_tag: token-classification
library_name: openmed
tags:
  - openmed
  - mlx
  - apple-silicon
  - zero-shot-ner
  - gliner
  - medical
  - clinical

OpenMed-ZeroShot-NER-Pharma-Small-166M for OpenMed MLX

This repository contains an OpenMed MLX conversion of OpenMed/OpenMed-ZeroShot-NER-Pharma-Small-166M for Apple Silicon inference with OpenMed.

Artifact metadata:

  • OpenMed MLX task: zero-shot-ner
  • OpenMed MLX family: gliner-uni-encoder-span
  • Weight format: safetensors
  • Runtime API: GLiNERMLXPipeline

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:

Quick Start 

pip install openmed
pip install "openmed[mlx]"

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

model_path = snapshot_download("OpenMed/OpenMed-ZeroShot-NER-Pharma-Small-166M-mlx")
pipe = GLiNERMLXPipeline(model_path)

entities = pipe.predict_entities(
    "Patient John Doe was seen at Stanford Hospital.",
    labels=["person", "organization", "location"],
    threshold=0.5,
)

for entity in entities:
    print(entity)

Prompt packing metadata included with the model:

{
  "kind": "gliner-words",
  "entity_token": "<<ENT>>",
  "separator_token": "<<SEP>>",
  "class_token_index": 128002,
  "embed_marker_token": true,
  "split_mode": "words"
}

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