He and Hofmann (arXiv:2311.01906) detailed a skipless transformer without the V and P (post-attention projection) linear layers, which reduces the total number of weights. However, this scheme is only applicable to MHA (multi-head attention), but not for MQA (multi-query attention) and GQA (grouped-query attention). The latter schemes are used by many popular LLMs such as Llama 2, Mistral, Mixtral, PaLM, and Gemma. Therefore, this micro-paper proposes mathematically equivalent versions that are suitable for MQA and GQA. For example, removing Q and P from a skipless version of Mistral-7B would remove 15% of its weights (and thus reduce its compute and memory complexity). Watch our explainer video https://youtu.be/Tx_lMpphd2g and see https://github.com/OpenMachine-ai/transformer-tricks for code and more transformer tricks.
Cite
@article{arxiv.2404.12362,
title = {KV-weights are all you need for skipless transformers},
author = {Nils Graef},
journal= {arXiv preprint arXiv:2404.12362},
year = {2025}
}