按年被提到
20232023 · 3 次2026
大模型与语言模型›量化、解码与分词·arXiv:2311.10770 · cs.CL

Exponentially Faster Language Modelling

Peter Belcak, Roger Wattenhofer · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 4 人首次 2023-11-21 · 最近 2024-09-23
4不同的人
2活跃月份
4讨论串
6被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Language models only really need to use an exponential fraction of their neurons for individual inferences. As proof, we present UltraFastBERT, a BERT variant that uses 0.3% of its neurons during inference while performing on par with similar BERT models. UltraFastBERT selectively engages just 12 out of 4095 neurons for each layer inference. This is achieved by replacing feedforward networks with fast feedforward networks (FFFs). While no truly efficient implementation currently exists to unlock the full acceleration potential of conditional neural execution, we provide high-level CPU code achieving 78x speedup over the optimized baseline feedforward implementation, and a PyTorch implementation delivering 40x speedup over the equivalent batched feedforward inference. We publish our training code, benchmarking setup, and model weights.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论WithinReason · 2024-09

“The only reason neural networks don't have control flow is because they are not very good. They are incredibly inefficient and the only way to properly solve that is to introduce control flow, for example: https://arxiv.org/abs/2311.10770”

Tinygrad will be the next Linux and LLVM原评论 ↗
被提交为 story · 3 次