onnxruntime VS transformers.js

ONNX Runtime: ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Embedding generation uses the ONNX runtime under the hood. This is a cross-platform inferencing library that supports multiple execution providers from CPU to specialized GPUs.

tfjs is dead, looking at the commit history. The standard now is to convert PyTorch to onnx, then use onnxruntime (https://github.com/microsoft/onnxruntime/tree/main/js/web) to run the model on the browsdr.

- slang[2] has the potential, but the meta programming part is not as strong as C++, existing libraries cannot be used.

The above conclusion is drawn from my work https://github.com/microsoft/onnxruntime/tree/dev/opencl, purely nightmare to work with thoes drivers and jit compilers. Hopefully Vcc can take compute shader more seriously.

[1]: https://www.circle-lang.org/

I did. It depends what you want, for an overview of how ONNX Runtime works then Microsoft have a bunch of things on https://onnxruntime.ai, but the Java content is a bit lacking on there as I've not had time to write much. Eventually I'll probably write something similar to the C# SD tutorial they have on there but for the Java API.

For writing ONNX models from Java we added an ONNX export system to Tribuo in 2022 which can be used by anything on the JVM to export ONNX models in an easier way than writing a protobuf directly. Tribuo doesn't have full coverage of the ONNX spec, but we're happy to accept PRs to expand it, otherwise it'll fill out as we need it.

What about models besides GPT? Most of the popular vector encoding models aren't using this architecture.

If you really didn't want PyTorch/Transformers, you could consider exporting your models to ONNX (https://github.com/microsoft/onnxruntime).

We have some other WebGPU demos, including:

- WebGPU embedding benchmark: https://huggingface.co/spaces/Xenova/webgpu-embedding-benchm...

- Real-time object detection: https://huggingface.co/spaces/Xenova/webgpu-video-object-det...

- Real-time background removal: https://huggingface.co/spaces/Xenova/webgpu-video-background...

- WebGPU depth estimation: https://huggingface.co/spaces/Xenova/webgpu-depth-anything

- Image background removal: https://huggingface.co/spaces/Xenova/remove-background-webgp...

You can follow the progress for full WebGPU support in the v3 development branch (https://github.com/xenova/transformers.js/pull/545).

To answer your question, while there are certain ops missing, the main limitation at the moment is for models with decoders... which are not very fast (yet) due to inefficient buffer reuse and many redundant copies between CPU and GPU. We're working closely with the ORT team to fix these issues though!

BTW: you might want to add support for typed arrays.

See: https://github.com/xenova/transformers.js/blob/8804c36591d11...

This is really old, but added as part of the shape of the vector as well: https://github.com/nicolaspanel/numjs/blob/master/src/dtypes...

Made possible by Xenova and Supabase / gte-small

To build the application, you’ll use the youtube-transcript package to retrieve YouTube video transcripts. You will then use LangChain and the Transformers.js package to generate free Hugging Face embeddings for the given transcript and store them in a vector store instead of relying on potentially expensive OpenAI embeddings. Lastly, you will use LangChain and an OpenAI model to retrieve information stored in the vector store.

Transformers.js: A groundbreaking library, Transformers.js brings transformer models like GPT-3, BERT, and Whisper straight to your browser. With the introduction of technologies like webGPU and LLM, Transformers.js has garnered significant attention. If you’d like to learn how to integrate a small model in the UI, check out their code and examples here.

The announcement seems somewhat disingenuous. The PR[1] found from their release notes[2] seems to contain only boilerplate and no real support for Mistral models or their weights.

[1]: https://github.com/xenova/transformers.js/pull/379