Document BUILDER_CONFIG_CLASS (huggingface#6166)

document BUILDER_CONFIG_CLASS

docs/source/dataset_script.mdx

@@ -144,6 +144,8 @@ class SuperGlueConfig(datasets.BuilderConfig):
 class SuperGlue(datasets.GeneratorBasedBuilder):
     """The SuperGLUE benchmark."""
 
+    BUILDER_CONFIG_CLASS = SuperGlueConfig
+
     BUILDER_CONFIGS = [
         SuperGlueConfig(
             name="boolq",
@@ -173,6 +175,13 @@ class SuperGlue(datasets.GeneratorBasedBuilder):
 >>> dataset = load_dataset('super_glue', 'boolq')
 ```
 
+Additionally, users can instantiate a custom builder configuration by passing the builder configuration arguments to [`load_dataset`]:
+
+```py
+>>> from datasets import load_dataset
+>>> dataset = load_dataset('super_glue', data_url="https://custom_url")
+```
+
 ### Default configurations
 
 Users must specify a configuration name when they load a dataset with multiple configurations. Otherwise, 🤗 Datasets will raise a `ValueError`, and prompt the user to select a configuration name. You can avoid this by setting a default dataset configuration with the `DEFAULT_CONFIG_NAME` attribute: