“Not really. They have a way of squaring this circle, by changing their inference code. Speculative sampling [1] would still make their first claim a lie – sure, there'd still be the original GPT-4 model, plus a smaller draft worker. But early exit decoding [2] allows you to get almost as good results for much cheaper from exactly the same checkpoint. We k…”
Confident Adaptive Language Modeling
Recent advances in Transformer-based large language models (LLMs) have led to significant performance improvements across many tasks. These gains come with a drastic increase in the models' size, potentially leading to slow and costly use at inference time. In practice, however, the series of generations made by LLMs is composed of varying levels of difficulty. While certain predictions truly benefit from the models' full capacity, other continuations are more trivial and can be solved with reduced compute. In this work, we introduce Confident Adaptive Language Modeling (CALM), a framework for dynamically allocating different amounts of compute per input and generation timestep. Early exit decoding involves several challenges that we address here, such as: (1) what confidence measure to use; (2) connecting sequence-level constraints to local per-token exit decisions; and (3) attending back to missing hidden representations due to early exits in previous tokens. Through theoretical analysis and empirical experiments on three diverse text generation tasks, we demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $\times 3$ -- while provably maintaining high performance.
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- Confident Adaptive Language Modeling ↗WolfOliver · 2022-12-22 · 2 分
- New framework increases speed of large language models by up to 3x ↗georgehill · 2022-12-27 · 1 分