Papers with high-temperature generation setting
Temperature-Centric Investigation of Speculative Decoding with Knowledge Distillation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Speculative decoding is a novel method to expedite inference in autoregressive (large) language models. |
| Approach: | They propose to use a smaller model as a draft model to speculate a block of tokens, which the target model then evaluates for acceptance. |
| Outcome: | The proposed method can be used to accelerate inference in autoregressive (large) language models by using smaller models as draft models to speculate tokens for multiple inference steps. |