Modelpublic

inference4j/distilbert-base-uncased-finetuned-sst-2-english

sourceHugging Faceapache-2.0updated 8mo agoView on Hugging Face

1likes19downloads

Model Card

DistilBERT SST-2 — ONNX

ONNX export of distilbert-base-uncased-finetuned-sst-2-english, a DistilBERT model fine-tuned on the Stanford Sentiment Treebank (SST-2) for binary sentiment classification (POSITIVE/NEGATIVE).

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

Original Source

—Repository: Xenova (originally distilbert-base by HuggingFace)
—License: apache-2.0

Usage with inference4j

java

try (DistilBertClassifier model = DistilBertClassifier.fromPretrained("models/distilbert-sst2")) {
    List<TextClassification> results = model.classify("This movie was fantastic!");
    System.out.println(results.get(0).label()); // "POSITIVE"
    System.out.printf("Score: %.4f%n", results.get(0).score());
}

Model Details

Property	Value
Architecture	DistilBERT (6 layers, 768 hidden)
Task	Binary sentiment classification (POSITIVE / NEGATIVE)
Training data	SST-2 (Stanford Sentiment Treebank)
Max sequence length	512
Original framework	PyTorch (HuggingFace Transformers)
ONNX export	By Xenova (Transformers.js)

License

This model is licensed under the Apache License 2.0. Original model by HuggingFace, ONNX export by Xenova.