Joshua Lochner

Thanks 👍 The first error message you received looks like a bug with optimum. If you'd like, you can [raise an issue](https://github.com/huggingface/optimum/issues/new?assignees=&labels=bug&template=bug-report.yml) on their repo. For now (even if you...

Right, it's failing because the .onnx file does not contain all the model parameters. Those parameters are stored in .onnx_data. This is due to a limitation with protobuf, which has...

Updated title to be a feature request for the external data file format (which is used for models larger than 2GB).

Hi there 👋 You can use the original [sam-vit-large](https://huggingface.co/facebook/sam-vit-large) model (linked in the readme of [Xenova/sam-vit-large](https://huggingface.co/Xenova/sam-vit-large)) if you want to use it from python. Example code: ```py from PIL import...

You can increase the opset value by adding `--opset 12` to the conversion command :) So, ``` python -m scripts.convert --quantize --model_id Twitter/twhin-bert-large --opset 12 ``` should work

If you are only using the model for embeddings (i.e., not masked language modelling, which the model was trained for), you should append `--task feature-extraction` to the conversion command. This...

> my call to const output = await classifier(image) as DepthEstimationPipelineOutput crashes my Electron app with no logs. Odd indeed! 🤔 If you are somehow able to retrieve the logs,...

Thanks for your extensive tests and analysis! 🤗 > failed to call OrtRun(). error code = 6. This usually happens with out-of-memory issues. Perhaps @guschmue can provide some insight/assistance? On...

Hi there! 👋 We do support a collection of OCR models (the [TrOCR](https://huggingface.co/models?library=transformers.js&other=trocr&sort=trending) model family). For example, https://huggingface.co/Xenova/trocr-small-handwritten can be used as follows: ```js import { pipeline } from '@xenova/transformers';...

Hi again 👋 Apologies for the late response! The transformers.js library aims to bring the [python transformers library](http://github.com/huggingface/transformers) to the browser and other JavaScript environments (e.g., Node, deno), so if...