1f489b2d6a7968e6a8a20ae3857a66f8939b5850,tensorflow_datasets/text/lm1b.py,Lm1b,Lm1b_1,#,94

Before Change

class Lm1b(tfds.core.GeneratorBasedBuilder):
  1 Billion Word Language Model Benchmark dataset.
  BUILDER_CONFIGS = [
      Lm1bConfig(
          name="plain_text",
          description="Plain text",
      ),
      Lm1bConfig(
          name="bytes",
          description=("Uses byte-level text encoding with "
                       "`tfds.deprecated.text.ByteTextEncoder`"),
          text_encoder_config=tfds.deprecated.text.TextEncoderConfig(
              encoder=tfds.deprecated.text.ByteTextEncoder()),
      ),
      Lm1bConfig(
          name="subwords8k",
          description=("Uses `tfds.deprecated.text.SubwordTextEncoder` with 8k "
                       "vocab size"),
          text_encoder_config=tfds.deprecated.text.TextEncoderConfig(
              encoder_cls=tfds.deprecated.text.SubwordTextEncoder,
              vocab_size=2**13),
      ),
      Lm1bConfig(
          name="subwords32k",
          description=("Uses `tfds.deprecated.text.SubwordTextEncoder` with "
                       "32k vocab size"),
          text_encoder_config=tfds.deprecated.text.TextEncoderConfig(
              encoder_cls=tfds.deprecated.text.SubwordTextEncoder,
              vocab_size=2**15),
      ),
  ]

  def _info(self):
    return tfds.core.DatasetInfo(
        builder=self,

After Change

class Lm1b(tfds.core.GeneratorBasedBuilder):
  1 Billion Word Language Model Benchmark dataset.

  VERSION = tfds.core.Version("1.1.0")

  def _info(self):
    return tfds.core.DatasetInfo(
        builder=self,

Instances