inference4j/distilbert-NER

DistilBERT NER — ONNX

ONNX export of dslim/distilbert-NER, a DistilBERT model fine-tuned on CoNLL-2003 for Named Entity Recognition. Identifies persons, organizations, locations, and miscellaneous entities in text using IOB2 tagging.

Mirrored for use with inference4j, an inference-only AI library for Java.

Original Source

• Repository: dslim (ONNX by onnx-community)
• License: apache-2.0

Usage with inference4j

try (BertNerRecognizer ner = BertNerRecognizer.builder()
        .modelId("inference4j/distilbert-NER")
        .build()) {
    List<NamedEntity> entities = ner.recognize("John works at Google in London.");
    for (NamedEntity e : entities) {
        System.out.printf("%s (%s)%n", e.text(), e.label());
    }
    // John (PER)
    // Google (ORG)
    // London (LOC)
}

Model Details

Property	Value
Architecture	DistilBERT (6 layers, 768 hidden, 66M params)
Task	Named Entity Recognition (IOB2 tagging)
Labels	O, B-PER, I-PER, B-ORG, I-ORG, B-LOC, I-LOC, B-MISC, I-MISC
Training data	CoNLL-2003
F1 score	92.17
Max sequence length	512
Tokenizer	WordPiece (cased)
Original framework	PyTorch (HuggingFace Transformers)

License

This model is licensed under the Apache License 2.0. Original model by dslim, ONNX export by onnx-community.