---
library_name: onnx
tags:
  - gte
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - onnx
  - inference4j
license: mit
pipeline_tag: sentence-similarity
---

# GTE Base — ONNX

ONNX export of [thenlper/gte-base](https://huggingface.co/thenlper/gte-base), an English embedding model from Alibaba. Maps sentences to 768-dimensional dense vectors using CLS pooling with L2 normalization.

Mirrored for use with [inference4j](https://github.com/inference4j/inference4j), an inference-only AI library for Java.

## Original Source

- **Repository:** [thenlper/Alibaba (ONNX by Xenova)](https://huggingface.co/thenlper/gte-base)
- **License:** mit

## Usage with inference4j

```java
try (SentenceTransformerEmbedder model = SentenceTransformerEmbedder.builder()
        .modelId("inference4j/gte-base")
        .poolingStrategy(PoolingStrategy.CLS)
        .normalize()
        .build()) {
    float[] embedding = model.encode("Hello, world!");
    System.out.println("Dimension: " + embedding.length); // 768
}
```

## Model Details

| Property | Value |
|----------|-------|
| Architecture | BERT Base (12 layers, 768 hidden) |
| Task | Sentence embeddings / semantic similarity |
| Output dimension | 768 |
| Pooling | CLS |
| Normalization | L2 |
| Max sequence length | 512 |
| Original framework | PyTorch (HuggingFace Transformers) |

## License

This model is licensed under the [MIT License](https://opensource.org/licenses/MIT). Original model by [thenlper/Alibaba](https://huggingface.co/thenlper/gte-base), ONNX export by [Xenova](https://huggingface.co/Xenova).