Downloads · 30 days
0
inference4j/all-mpnet-base-v2
all-mpnet-base-v2 is a sentence similarity model from inference4j. Use it when you need a score for how close two texts are. It is set up for onnx. The card lists the license as apache-2.0.
ONNX export of all-mpnet-base-v2, the highest-quality sentence-transformers model based on MPNet. Maps sentences to a 768-dimensional dense vector space.
Downloads · 30 days
0
Access
Public
Updated Feb 13, 2026
Repo size
436 MB
Likes
0
Public
Click a slice to open those files.
.onnx436 MB · 100%
From the Hugging Face model README
ONNX export of all-mpnet-base-v2, the highest-quality sentence-transformers model based on MPNet. Maps sentences to a 768-dimensional dense vector space.
Mirrored for use with inference4j, an inference-only AI library for Java.
try (SentenceTransformer model = SentenceTransformer.fromPretrained("models/all-mpnet-base-v2")) {
float[] embedding = model.encode("Hello, world!");
System.out.println("Dimension: " + embedding.length); // 768
}
| Property | Value |
|---|---|
| Architecture | MPNet-base (12 layers, 768 hidden) |
| Task | Sentence embeddings / semantic similarity |
| Output dimension | 768 |
| Max sequence length | 384 |
| Training data | 1B+ sentence pairs |
| Original framework | PyTorch (sentence-transformers) |
This model is licensed under the Apache License 2.0. Original model by sentence-transformers.