all-MiniLM-L12-v2 — ONNX

ONNX export of all-MiniLM-L12-v2, a sentence-transformers model that maps sentences to a 384-dimensional dense vector space. Deeper variant (12 layers) of MiniLM with slightly better quality at the cost of speed.

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

Original Source

• Repository: sentence-transformers
• License: apache-2.0

Usage with inference4j

try (SentenceTransformer model = SentenceTransformer.fromPretrained("models/all-MiniLM-L12-v2")) {
    float[] embedding = model.encode("Hello, world!");
    System.out.println("Dimension: " + embedding.length); // 384
}

Model Details

Property	Value
Architecture	MiniLM-L12 (12 layers, 384 hidden)
Task	Sentence embeddings / semantic similarity
Output dimension	384
Max sequence length	256
Training data	1B+ sentence pairs
Original framework	PyTorch (sentence-transformers)

License

This model is licensed under the Apache License 2.0. Original model by sentence-transformers.