Gorgonia VS transformers

GitHub - gorgonia/gorgonia: Gorgonia is a library that helps facilitate machine learning in Go.

I did end up writing and using a custom library for Random Forest (it's also in AwesomGo) in one real-world project (detecting Alzheimer's and Parkinson's from speech from a mobile app) - https://github.com/malaschitz/randomForest I had better results than the team who used TensorFlow and most importantly I didn't have to use any other technology than Go. For NN's it's probably best to use https://gorgonia.org/ - but it's not exactly a user friendly library. But there is a whole book on it - Hands-On Deep Learning with Go.

Perhaps it's a product of French culture, but because Gorgonia[0] has a number of French contributors, this was actually the way we structured our documentation.

But this is the first time I've heard of the name of the framework.

[0]: https://gorgonia.org

Oh it's.Gorgonia

Website: https://gorgonia.org

I use Gorgonia.

What you think about this https://github.com/gorgonia/gorgonia ? I also recall there is something else out there but can't find it at the moment...

Yep, all of them: https://github.com/gorgonia/gorgonia

transformers is a package by Hugging Face, that helps you interact with models on HF Hub (GitHub)

Is t5x an encoder/decoder architecture?

Some more general options.

The Flax ecosystem

https://github.com/google/flax?tab=readme-ov-file

or dm-haiku

https://github.com/google-deepmind/dm-haiku

were some of the best developed communities in the Jax AI field

Perhaps the “trax” repo? https://github.com/google/trax

Some HF examples https://github.com/huggingface/transformers/tree/main/exampl...

Sadly it seems much of the work is proprietary these days, but one example could be Grok-1, if you customize the details. https://github.com/xai-org/grok-1/blob/main/run.py

The HuggingFace transformers library already has support for a similar method called prompt lookup decoding that uses the existing context to generate an ngram model: https://github.com/huggingface/transformers/issues/27722

I don't think it would be that hard to switch it out for a pretrained ngram model.

Most of this tutorial is based on Hugging Face course about Transformers and on Niels Rogge's Transformers tutorials: make sure to check their work and give them a star on GitHub, if you please ❤️

* Superconvergence + LR range finder + Fast AI's Ranger21 optimizer was the goto optimizer for CNNs, and worked fabulously well, but on transformers, the learning rate range finder sadi 1e-3 was the best, whilst 1e-5 was better. However, the 1 cycle learning rate stuck. https://github.com/huggingface/transformers/issues/16013

Thanks! :) I'm pushing them into transformers, pytorch-gemma and collabing with the Gemma team to resolve all the issues :)

The RoPE fix should already be in transformers 4.38.2: https://github.com/huggingface/transformers/pull/29285

My main PR for transformers which fixes most of the issues (some still left): https://github.com/huggingface/transformers/pull/29402

If you want to tinker with the architecture Hugging Face has a FOSS implementation in transformers: https://github.com/huggingface/transformers/blob/main/src/tr...

If you want to reproduce the training pipeline, you couldn't do that even if you wanted to because you don't have access to thousands of A100s.