diff --git a/content/essays/attention-and-multiattention.md b/content/essays/attention-and-multiattention.md index 1614088..12d3b10 100644 --- a/content/essays/attention-and-multiattention.md +++ b/content/essays/attention-and-multiattention.md @@ -1,5 +1,5 @@ --- -title: "Attention and Multiattention" +title: "自注意力和多头注意力" date: 2022-09-19T20:35:33+08:00 tags: [] categories: [] @@ -27,11 +27,11 @@ $$ $$ head_1 = Attention(W_1^QQ, W_1^K, W_1^VV) -\\ +\\\\ head_2 = Attention(W_2^QQ, W_2^K, W_2^VV) -\\ +\\\\ head_3 = Attention(W_3^QQ, W_3^K, W_3^VV) -\\ +\\\\ head_4 = Attention(W_4^QQ, W_4^K, W_4^VV) $$