[–] wicket 5mo ago ↗ Related paperBitNet: Scaling 1-bit Transformers for Large Language Models (2023): https://arxiv.org/abs/2310.11453
[–] vhodges 5mo ago ↗ This came out too close to April 1 for me to know if it was real or not :).I do like the idea of local/on device llms so it's interesting and will keep an eye on it.
2 comments
[ 5.3 ms ] story [ 51.2 ms ] threadBitNet: Scaling 1-bit Transformers for Large Language Models (2023): https://arxiv.org/abs/2310.11453
I do like the idea of local/on device llms so it's interesting and will keep an eye on it.