You can deploy this model and start earning money today!

onnx-community/
paligemma2-3b-pt-448

Name: paligemma2-3b-pt-448
Availability: InStock

google/paligemma2-3b-pt-448

quantized

Views

No views yet

https://huggingface.co/google/paligemma2-3b-pt-448 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: Image captioning with onnx-community/paligemma2-3b-pt-448.

import { AutoProcessor, PaliGemmaForConditionalGeneration, load_image } from '@huggingface/transformers';

// Load processor and model
const model_id = 'onnx-community/paligemma2-3b-pt-448';
const processor = await AutoProcessor.from_pretrained(model_id);
const model = await PaliGemmaForConditionalGeneration.from_pretrained(model_id, {
    dtype: {
        embed_tokens: 'fp16', // or 'q8'
        vision_encoder: 'fp16', // or 'q4', 'q8'
        decoder_model_merged: 'q4', // or 'q4f16'
    },
});

// Prepare inputs
const url = 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg'
const raw_image = await load_image(url);
const prompt = '<image>'; // Caption, by default
const inputs = await processor(raw_image, prompt);

// Generate a response
const output = await model.generate({
    ...inputs,
    max_new_tokens: 100,
})

const generated_ids = output.slice(null, [inputs.input_ids.dims[1], null]);
const answer = processor.batch_decode(
    generated_ids,
    { skip_special_tokens: true },
);
console.log(answer[0]);
// a blue and white car parked on a street

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).