mesh-transformer-jax VS transformers

GPT-J is a LLM case study with two goals: Training a LLM with a data source containing unique material, and using the training frameworkMesh Transformer JAX to achieve a high training efficiency through parallelization. There is no research paper about GPT-J, but on its GitHub pages, the model, different checkpoints, and the complete source code for training is given.

This idea has already been proposed in ViT-22B and GPT-J-6B.

Sure. Here's the repo I used for the fine-tuning: https://github.com/kingoflolz/mesh-transformer-jax. I used 5 epochs, and appart from that I kept the default parameters in the repo.

You can skip to step 4 using something like GPT-J as far as I understand: https://github.com/kingoflolz/mesh-transformer-jax#links

The pretrained model is already available.

The Github repo suggests it's possible you can change the number of checkpoints to make it run on a GPU.

GPT-J, which uses mesh-transformer-jax: https://github.com/kingoflolz/mesh-transformer-jax

They hinted at it in the screenshot, but the goods are linked from the https://6b.eleuther.ai page: https://github.com/kingoflolz/mesh-transformer-jax#gpt-j-6b (Apache 2)

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.