AutoGPTQ VS transformers

Deploying the 60B version is a challenge though and you might need to apply 4-bit quantization with something like https://github.com/PanQiWei/AutoGPTQ or https://github.com/qwopqwop200/GPTQ-for-LLaMa . Then you can improve the inference speed by using https://github.com/turboderp/exllama .

If you prefer to use an "instruct" model à la ChatGPT (i.e. that does not need few-shot learning to output good results) you can use something like this: https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Uncensored...

AutoGPTQ: an attempt at standardizing GPTQ-for-LLaMa and turning it into a library that is easier to install and use, and that supports more models. https://github.com/PanQiWei/AutoGPTQ

Just use the script: https://github.com/PanQiWei/AutoGPTQ/blob/main/examples/quantization/quant_with_alpaca.py

In the wild, people tend to use GTPQ quantization for pure GPU inference: https://github.com/PanQiWei/AutoGPTQ

And ggml's quant for CPU inference with some offload, which just got updated to a more GPTQ-like method days ago: https://github.com/ggerganov/llama.cpp/pull/1684

Some other runtimes like Apache TVM also have their own quant implementations: https://github.com/mlc-ai/mlc-llm

For training, 4-bit bitsandbytes is SOTA, as far as I know.

TBH I'm not sure why this November paper is being linked. Few are running 8 bit models when they could fit a better 3-5 bit model in the same memory pool.

Instead of integrating GPTQ-for-Lllama, use AutoGPTQ instead.

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.