---
title: bge-small-zh-v1.5-ONNX
canonical_url: "https://www.modelscope.cn/models/onnx-community/bge-small-zh-v1.5-ONNX"
md_url: "https://www.modelscope.cn/models/onnx-community/bge-small-zh-v1.5-ONNX.md"
repository: onnx-community/bge-small-zh-v1.5-ONNX
last_updated: 2026-01-15
pipeline_tag: feature-extraction
tasks:
  - feature-extraction
model_type:
  - bert
architectures:
  - BertModel
base_model:
  - BAAI/bge-small-zh-v1.5
base_model_relation: finetune
library_name:
  - onnx
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 592
stars: 2
---

# bge-small-zh-v1.5-ONNX

> bge-small-zh-v1.5-ONNX - onnx-community 在 ModelScope 开源的模型。https://huggingface.co/BAAI/bge-small-zh-v1.5 with ONNX weights to be compatible with Transformers.js.

onnx-community/bge-small-zh-v1.5-ONNX 是 ModelScope 魔搭社区上的feature-extraction模型，基于 BAAI/bge-small-zh-v1.5 构建，可用 deploy_task emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: onnx-community/bge-small-zh-v1.5-ONNX
- **Tasks**: feature-extraction
- **Base model**: BAAI/bge-small-zh-v1.5
- **Inference backends**: deploy_task emb, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 592
- **Stars**: 2
- **Last updated**: 2026-01-15

Source: https://www.modelscope.cn/models/onnx-community/bge-small-zh-v1.5-ONNX

---

https://huggingface.co/BAAI/bge-small-zh-v1.5 with ONNX weights to be compatible with Transformers.js.

## Usage (Transformers.js)

If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using:
```bash
npm i @huggingface/transformers
```

**Example:** Run feature extraction.

```js
import { pipeline } from '@huggingface/transformers';

const extractor = await pipeline('feature-extraction', 'Xenova/bge-small-zh-v1.5');
const output = await extractor('This is a simple test.');
```

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).