From a109b3fc32d255d03e9130e0fc28a10b7900873d Mon Sep 17 00:00:00 2001 From: pglorio <85982602+pglorio@users.noreply.github.com> Date: Fri, 27 Sep 2024 13:48:18 -0700 Subject: [PATCH] Added doc for attention_head_size --- src/transformers/models/zamba/configuration_zamba.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/src/transformers/models/zamba/configuration_zamba.py b/src/transformers/models/zamba/configuration_zamba.py index 77d759d70d467a..82ddec7f1ed739 100644 --- a/src/transformers/models/zamba/configuration_zamba.py +++ b/src/transformers/models/zamba/configuration_zamba.py @@ -44,6 +44,8 @@ class ZambaConfig(PretrainedConfig): model has a output word embedding layer. hidden_size (`int`, *optional*, defaults to 3712): Dimension of the hidden representations. + attention_hidden_size (`int`, *optional*, defaults to `None`): + Dimension of the hidden representations of the inputs to the Attention layer. intermediate_size (`int`, *optional*, defaults to 14848): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 76):