Instructions to use Xenova/moondream2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use Xenova/moondream2 with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-text-to-text', 'Xenova/moondream2');
Unsupported pipeline: image-text-to-text
#1
by Paladosss - opened
Error: Unsupported pipeline: image-text-to-text. Must be one of [...you now...]
Should I use it in a different way?
Not like in the instructions </> Use in Transformers.js?
Or just wait for the update Transformers.js?
In case with AutoModelForCausalLM => Error: Unsupported model type: moondream1
Hi there ๐ Weโre still busy adding support for this model to transformers.js, and Iโll update the model card when itโs ready! ๐ค
I've updated the model card with example code!
We also released an online demo, which you can try yourself: https://huggingface.co/spaces/Xenova/experimental-moondream-webgpu