Unverified Commit 66828a19 authored by Yih-Dar's avatar Yih-Dar Committed by GitHub
Browse files

Fix Funnel configuration doc (#15686)



* fix doc

* make style
Co-authored-by: default avatarydshieh <ydshieh@users.noreply.github.com>
parent 3a4376d0
...@@ -77,8 +77,7 @@ class FunnelConfig(PretrainedConfig): ...@@ -77,8 +77,7 @@ class FunnelConfig(PretrainedConfig):
type_vocab_size (`int`, *optional*, defaults to 3): type_vocab_size (`int`, *optional*, defaults to 3):
The vocabulary size of the `token_type_ids` passed when calling [`FunnelModel`] or [`TFFunnelModel`]. The vocabulary size of the `token_type_ids` passed when calling [`FunnelModel`] or [`TFFunnelModel`].
initializer_range (`float`, *optional*, defaults to 0.1): initializer_range (`float`, *optional*, defaults to 0.1):
The standard deviation of the *uniform initializer* for initializing all weight matrices in attention The upper bound of the *uniform initializer* for initializing all weight matrices in attention layers.
layers.
initializer_std (`float`, *optional*): initializer_std (`float`, *optional*):
The standard deviation of the *normal initializer* for initializing the embedding matrix and the weight of The standard deviation of the *normal initializer* for initializing the embedding matrix and the weight of
linear layers. Will default to 1 for the embedding matrix and the value given by Xavier initialization for linear layers. Will default to 1 for the embedding matrix and the value given by Xavier initialization for
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment