Xenova/all-mpnet-base-v2
作者 Xenova | 下载 13K | 点赞 4 | 更新 2025-07-22
这个仓库里有什么
- 8 个 ONNX 模型(.onnx 文件)
- 15 个文件,其中 .onnx 8 个、.json 4 个、.md 1 个、.txt 1 个
- 仓库体积约 1.3 GB
- 最近更新:2025-07-22
ONNX 文件清单
| 文件 | 大小 | 下载 |
|---|---|---|
| onnx/model.onnx | 416 MB | 下载 |
| onnx/model_bnb4.onnx | 137 MB | 下载 |
| onnx/model_fp16.onnx | 208 MB | 下载 |
| onnx/model_int8.onnx | 105 MB | 下载 |
| onnx/model_q4.onnx | 142 MB | 下载 |
| onnx/model_q4f16.onnx | 91.5 MB | 下载 |
| onnx/model_quantized.onnx | 105 MB | 下载 |
| onnx/model_uint8.onnx | 105 MB | 下载 |
怎么用
这些 ONNX 文件可以直接用 ONNX Runtime 加载运行;想先看网络结构,可以把文件上传到 Netron 在线查看器 查看。下载链接指向 Hugging Face 原始文件。
说明文档
https://huggingface.co/sentence-transformers/all-mpnet-base-v2 with ONNX weights to be compatible with Transformers.js.
Usage (Transformers.js)
If you haven't already, you can install the Transformers.js JavaScript library from NPM using:
npm i @huggingface/transformers
Example: Run feature extraction.
import { pipeline } from '@huggingface/transformers';
const extractor = await pipeline('feature-extraction', 'Xenova/all-mpnet-base-v2');
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 and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).
模型信息
创建时间: 2023-05-23
更新时间: 2025-07-22
在 Hugging Face 上查看