加载中…
加载中…
onnx/model.onnx 606 MBonnx/vision_model.onnx 352 MBonnx/model_fp16.onnx 304 MBonnx/text_model.onnx 254 MBonnx/model_q4.onnx 189 MBonnx/model_bnb4.onnx 182 MBonnx/vision_model_fp16.onnx 176 MBonnx/model_quantized.onnx 154 MBonnx/model_uint8.onnx 153 MBonnx/text_model_fp16.onnx 127 MBonnx/model_q4f16.onnx 126 MBonnx/text_model_q4.onnx 126 MBonnx/text_model_bnb4.onnx 123 MBonnx/vision_model_quantized.onnx 89 MBonnx/vision_model_uint8.onnx 89 MBonnx/vision_model_int8.onnx 89 MBonnx/text_model_q4f16.onnx 73 MBonnx/text_model_quantized.onnx 65 MBonnx/text_model_uint8.onnx 64 MBonnx/text_model_int8.onnx 64 MBonnx/vision_model_q4.onnx 64 MBonnx/vision_model_bnb4.onnx 58 MBonnx/vision_model_q4f16.onnx 53 MBhttps://huggingface.co/openai/clip-vit-base-patch32 with ONNX weights to be compatible with Transformers.js.
If you haven't already, you can install the Transformers.js JavaScript library from NPM using:
npm i @huggingface/transformers
Example: Perform zero-shot image classification with the pipeline API.
import { pipeline } from '@huggingface/transformers';
const classifier = await pipeline('zero-shot-image-classification', 'Xenova/clip-vit-base-patch32');
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/tiger.jpg';
const output = await classifier(url, ['tiger', 'horse', 'dog']);
// [
// { score: 0.9993917942047119, label: 'tiger' },
// { score: 0.0003519294841680676, label: 'horse' },
// { score: 0.0002562698791734874, label: 'dog' }
// ]
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).