small fix on idefics (#954)
transposing the fixes from https://github.com/huggingface/transformers/pull/25787
This commit is contained in:
parent
4f5d93ecd0
commit
2bc287bfcd
|
@ -51,7 +51,7 @@ class IdeficsVisionConfig(PretrainedConfig):
|
|||
Number of attention heads for each attention layer in the Transformer encoder.
|
||||
image_num_channels (`int`, *optional*, defaults to `3`):
|
||||
Number of image channels.
|
||||
hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`):
|
||||
hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
|
||||
The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
|
||||
`"relu"`, `"selu"` and `"gelu_new"` ``"quick_gelu"` are supported.
|
||||
layer_norm_eps (`float`, *optional*, defaults to 1e-5):
|
||||
|
@ -80,7 +80,7 @@ class IdeficsVisionConfig(PretrainedConfig):
|
|||
num_hidden_layers=32,
|
||||
num_attention_heads=16,
|
||||
num_channels=3,
|
||||
hidden_act="quick_gelu",
|
||||
hidden_act="gelu",
|
||||
layer_norm_eps=1e-5,
|
||||
attention_dropout=0.0,
|
||||
initializer_range=0.02,
|
||||
|
|
Loading…
Reference in New Issue