---
license: mit
base_model: google/embeddinggemma-300m
pipeline_tag: sentence-similarity
library_name: onnx
language:
- multilingual
tags:
- embedding
- onnx
---

# ONNX - embeddinggemma-300m
FP32 = model.onnx, model.onnx_data

INT8 = model_quantized.onnx, model_quantized.onnx_data

## Usage

```
# onnxruntime-gpu for run it on GPU
pip install onnxruntime sentencepiece numpy
```

- [src/helper.py](src/helper.py) = onnx session builder (provider selection, threads, memory options)
- [src/example.py](src/example.py) = full pipeline: sentencepiece tokenization, batching, inference, cosine similarity

```
python3 src/example.py
```

```
0.600231 | The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear, is a bear species endemic to China.
0.153004 | hi
0.554038 | パンダはクマ科の哺乳類で、中国の固有種である。
```

Note:
- No transformers/tokenizers dependency: the tokenizer is `tokenizer.model` directly with the native ids<br>
(bos_id, eos_id, pad_id from the sentencepiece model).
- Prompt prefix per mode:<br>
document = `title: none | text: {text}`<br>
query = `task: search result | query: {text}`
- Input format: `[bos] text [eos]`, padded per batch to the longest sequence.
- Output = `sentence_embedding`, 768 dimensions.
- Normalize input with NFKC for consistent multilingual scores.