| base_model: jinaai/jina-embeddings-v2-base-zh | |
| language: | |
| - zh | |
| - en | |
| library_name: transformers.js | |
| license: apache-2.0 | |
| tags: | |
| - feature-extraction | |
| - sentence-similarity | |
| - mteb | |
| - sentence_transformers | |
| - transformers | |
| inference: false | |
| https://huggingface.co/jinaai/jina-embeddings-v2-base-zh 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 | |
| ``` | |
| You can then use the model to compute embeddings, as follows: | |
| ```js | |
| import { pipeline, cos_sim } from '@huggingface/transformers'; | |
| // Create a feature extraction pipeline | |
| const extractor = await pipeline('feature-extraction', 'Xenova/jina-embeddings-v2-base-zh', { | |
| dtype: "fp32" // Options: "fp32", "fp16", "q8", "q4" | |
| }); | |
| // Compute sentence embeddings | |
| const texts = ['How is the weather today?', '今天天气怎么样?']; | |
| const output = await extractor(texts, { pooling: 'mean', normalize: true }); | |
| // Tensor { | |
| // dims: [2, 768], | |
| // type: 'float32', | |
| // data: Float32Array(1536)[...], | |
| // size: 1536 | |
| // } | |
| // Compute cosine similarity between the two embeddings | |
| const score = cos_sim(output[0].data, output[1].data); | |
| console.log(score); | |
| // 0.7860610759096025 | |
| ``` | |
| --- | |
| 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`). |