Talking-Heads Attention
read the original abstract
We introduce "talking-heads attention" - a variation on multi-head attention which includes linearprojections across the attention-heads dimension, immediately before and after the softmax operation.While inserting only a small number of additional parameters and a moderate amount of additionalcomputation, talking-heads attention leads to better perplexities on masked language modeling tasks, aswell as better quality when transfer-learning to language comprehension and question answering tasks.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Motion-Compensated Weight Compression
MCWC aligns permutation-symmetric blocks across layers to enable sequential prediction and residual entropy coding, improving rate-accuracy tradeoffs versus quantization and prior codecs on language and vision models.
-
Position-Agnostic Pre-Projection for Transformer Attention: Nonlinear Feature Construction and Content Skip Before Q/K/V
A position-agnostic nonlinear pre-projection MLP plus content skip connection in transformer attention improves LAMBADA accuracy by 40.6% and reduces perplexity by 39% on 160M-scale models.
-
TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models
TalkLoRA equips MoE-LoRA experts with a communication module that smooths routing dynamics and improves performance on language tasks under similar parameter budgets.
-
Nexusformer: Nonlinear Attention Expansion for Stable and Inheritable Transformer Scaling
Nexusformer uses a three-stage nonlinear mapping in attention to enable stable, inheritable scaling of transformers, matching baseline perplexity with up to 41.5% less compute when growing from 240M to 440M parameters.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.