From 0a0476cbfd6677f51975e0b5485fca91596ab8b5 Mon Sep 17 00:00:00 2001 From: shadeMe Date: Tue, 8 Aug 2023 13:17:20 +0200 Subject: [PATCH] Fix transformer listener naming --- website/docs/api/curated-transformer.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/api/curated-transformer.mdx b/website/docs/api/curated-transformer.mdx index 6fcb36765..9bd48d786 100644 --- a/website/docs/api/curated-transformer.mdx +++ b/website/docs/api/curated-transformer.mdx @@ -259,7 +259,7 @@ layers. The `CuratedTransformer` component therefore does not perform a weight update during its own `update` method. Instead, it runs its transformer model and communicates the output and the backpropagation callback to any downstream -components that have been connected to it via the TransformerListener sublayer. +components that have been connected to it via the transformer listener sublayer. If there are multiple listeners, the last layer will actually backprop to the transformer and call the optimizer, while the others simply increment the gradients.