Compsci Weekly on Nostr: [R] The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits ...

[R] The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

https://arxiv.org/abs/2402.17764

Discussions: https://discu.eu/q/https://arxiv.org/abs/2402.17764

#compsci #machinelearning