Update XXXForSequence with multilabel and activation function

docs/en/transformer_entries/AlbertForSequenceClassification.md

@@ -4,7 +4,9 @@ AlbertForSequenceClassification
 
 {%- capture description -%}
 AlbertForSequenceClassification can load ALBERT Models with sequence classification/regression head on top
-(a linear layer on top of the pooled output) e.g. for multi-class document classification tasks.
+(a linear layer on top of the pooled output), e.g. for document classification tasks.
+
+For multi-class, use `setActivation("softmax")`. For multi-label, use `setActivation("sigmoid")`.
 
 Pretrained models can be loaded with `pretrained` of the companion object:
 ```
@@ -125,4 +127,4 @@ scala_example=scala_example
 api_link=api_link
 python_api_link=python_api_link
 source_link=source_link
-%}
+%}

docs/en/transformer_entries/BertForSequenceClassification.md

@@ -3,8 +3,9 @@ BertForSequenceClassification
 {%- endcapture -%}
 
 {%- capture description -%}
-BertForSequenceClassification can load Bert Models with sequence classification/regression head on top (a linear layer on top of the pooled output)
-e.g. for multi-class document classification tasks.
+BertForSequenceClassification can load Bert Models with sequence classification/regression head on top (a linear layer on top of the pooled output), e.g. for document classification tasks.
+
+For multi-class, use `setActivation("softmax")`. For multi-label, use `setActivation("sigmoid")`.
 
 Pretrained models can be loaded with `pretrained` of the companion object:
 ```
@@ -127,4 +128,4 @@ scala_example=scala_example
 python_api_link=python_api_link
 api_link=api_link
 source_link=source_link
-%}
+%}

docs/en/transformer_entries/CamemBertForSequenceClassification.md

@@ -4,8 +4,9 @@ CamemBertForSequenceClassification
 
 {%- capture description -%}
 CamemBertForSequenceClassification can load CamemBERT Models with sequence
-classification/regression head on top (a linear layer on top of the pooled output) e.g. for
-multi-class document classification tasks.
+classification/regression head on top (a linear layer on top of the pooled output), e.g. for document classification tasks.
+
+For multi-class, use `setActivation("softmax")`. For multi-label, use `setActivation("sigmoid")`.
 
 Pretrained models can be loaded with `pretrained` of the companion object:
 
@@ -126,4 +127,4 @@ scala_example=scala_example
 api_link=api_link
 python_api_link=python_api_link
 source_link=source_link
-%}
+%}

docs/en/transformer_entries/DistilBertForSequenceClassification.md

@@ -4,7 +4,9 @@ DistilBertForSequenceClassification
 
 {%- capture description -%}
 DistilBertForSequenceClassification can load DistilBERT Models with sequence classification/regression head on top
-(a linear layer on top of the pooled output) e.g. for multi-class document classification tasks.
+(a linear layer on top of the pooled output), e.g. for document classification tasks.
+
+For multi-class, use `setActivation("softmax")`. For multi-label, use `setActivation("sigmoid")`.
 
 Pretrained models can be loaded with `pretrained` of the companion object:
 ```
@@ -126,4 +128,4 @@ scala_example=scala_example
 api_link=api_link
 python_api_link=python_api_link
 source_link=source_link
-%}
+%}

docs/en/transformer_entries/LongformerForSequenceClassification.md

@@ -4,7 +4,9 @@ LongformerForSequenceClassification
 
 {%- capture description -%}
 LongformerForSequenceClassification can load Longformer Models with sequence classification/regression head on top
-(a linear layer on top of the pooled output) e.g. for multi-class document classification tasks.
+(a linear layer on top of the pooled output), e.g. for document classification tasks.
+
+For multi-class, use `setActivation("softmax")`. For multi-label, use `setActivation("sigmoid")`.
 
 Pretrained models can be loaded with `pretrained` of the companion object:
 ```
@@ -124,4 +126,4 @@ scala_example=scala_example
 api_link=api_link
 python_api_link=python_api_link
 source_link=source_link
-%}
+%}

docs/en/transformer_entries/RoBertaForSequenceClassification.md

@@ -4,7 +4,9 @@ RoBertaForSequenceClassification
 
 {%- capture description -%}
 RoBertaForSequenceClassification can load RoBERTa Models with sequence classification/regression head on top
-(a linear layer on top of the pooled output) e.g. for multi-class document classification tasks.
+(a linear layer on top of the pooled output), e.g. for document classification tasks.
+
+For multi-class, use `setActivation("softmax")`. For multi-label, use `setActivation("sigmoid")`.
 
 Pretrained models can be loaded with `pretrained` of the companion object:
 ```
@@ -120,4 +122,4 @@ scala_example=scala_example
 api_link=api_link
 python_api_link=python_api_link
 source_link=source_link
-%}
+%}

docs/en/transformer_entries/XlmRoBertaForSequenceClassification.md

@@ -4,7 +4,9 @@ XlmRoBertaForSequenceClassification
 
 {%- capture description -%}
 XlmRoBertaForSequenceClassification can load XLM-RoBERTa Models with sequence classification/regression head on top
-(a linear layer on top of the pooled output) e.g. for multi-class document classification tasks.
+(a linear layer on top of the pooled output), e.g. for document classification tasks.
+
+For multi-class, use `setActivation("softmax")`. For multi-label, use `setActivation("sigmoid")`.
 
 Pretrained models can be loaded with `pretrained` of the companion object:
 ```
@@ -124,4 +126,4 @@ scala_example=scala_example
 api_link=api_link
 python_api_link=python_api_link
 source_link=source_link
-%}
+%}