banhxeo package

banhxeo.set_default_gpu()

Subpackages

• banhxeo.core package
  • NLTKTokenizer
    • NLTKTokenizer.tokenize()
    • NLTKTokenizer.detokenize()
  • Tokenizer
    • Tokenizer.tokenize()
    • Tokenizer.encode()
    • Tokenizer.batch_encode()
    • Tokenizer.train_from_iterator()
    • Tokenizer.save_pretrained()
    • Tokenizer.from_pretrained()
  • TokenizerConfig
    • TokenizerConfig.add_special_tokens
    • TokenizerConfig.max_length
    • TokenizerConfig.truncation
    • TokenizerConfig.padding
    • TokenizerConfig.check_padding()
    • TokenizerConfig.model_config
  • VocabConfig
    • VocabConfig.min_freq
    • VocabConfig.pad_tok
    • VocabConfig.unk_tok
    • VocabConfig.bos_tok
    • VocabConfig.sep_tok
    • VocabConfig.cls_tok
    • VocabConfig.mask_tok
    • VocabConfig.resv_tok
    • VocabConfig.check_min_freq_positive()
    • VocabConfig.special_tokens
    • VocabConfig.special_token_idx()
    • VocabConfig.model_config
  • Vocabulary
    • Vocabulary.__init__()
    • Vocabulary.load()
    • Vocabulary.build()
    • Vocabulary.save()
    • Vocabulary.vocab_size
    • Vocabulary.get_vocab()
    • Vocabulary.unk_id
    • Vocabulary.pad_id
    • Vocabulary.bos_id
    • Vocabulary.sep_id
    • Vocabulary.sep
    • Vocabulary.unk_tok
    • Vocabulary.bos_toks
    • Vocabulary.sep_toks
    • Vocabulary.token_to_idx
    • Vocabulary.idx_to_token
    • Vocabulary.tokens_to_ids()
    • Vocabulary.ids_to_tokens()
    • Vocabulary.get_word_counts()
  • Submodules
    • banhxeo.core.tokenizer module
      • TokenizerConfig
      • Tokenizer
      • NLTKTokenizer
    • banhxeo.core.vocabulary module
      • VocabConfig
      • Vocabulary
• banhxeo.data package
  • BaseTextDataset
    • BaseTextDataset.__init__()
    • BaseTextDataset.get_all_texts()
    • BaseTextDataset.get_data()
    • BaseTextDataset.to_torch_dataset()
    • BaseTextDataset.load_from_huggingface()
    • BaseTextDataset.inspect_huggingface_dataset()
  • IMDBDataset
    • IMDBDataset.__init__()
  • AmazonReviewFullDataset
    • AmazonReviewFullDataset.__init__()
  • Subpackages
    • banhxeo.data.dataset package
      • Submodules
  • Submodules
    • banhxeo.data.base module
      • BaseTextDataset
    • banhxeo.data.config module
      • DatasetSplit
      • DownloadDatasetFile
      • DatasetConfig
      • TorchDatasetConfig
    • banhxeo.data.torch module
      • TorchTextDataset
    • banhxeo.data.transforms module
      • Transforms
      • ComposeTransforms
      • RemoveHTMLTag
      • RemoveURL
      • RemovePunctuation
      • Strip
      • SpellingCorrection
• banhxeo.model package
  • LSTM
    • LSTM.__init__()
    • LSTM.forward()
  • MLP
    • MLP.ConfigClass
    • MLP.__init__()
    • MLP.forward()
    • MLP.generate_sequence()
  • RNN
    • RNN.__init__()
    • RNN.forward()
  • NGram
    • NGram.ConfigClass
    • NGram.__init__()
    • NGram.fit()
    • NGram.generate_sequence()
  • Subpackages
    • banhxeo.model.classic package
      • Submodules
    • banhxeo.model.llm package
      • Subpackages
      • Submodules
    • banhxeo.model.old package
      • Submodules
  • Submodules
    • banhxeo.model.base module
      • BaseLanguageModel
    • banhxeo.model.config module
      • ModelConfig
      • GenerateConfig
    • banhxeo.model.neural module
      • NeuralModelConfig
      • NeuralLanguageModel
• banhxeo.train package
  • Submodules
    • banhxeo.train.callbacks module
      • TrainerCallback
      • ProgressCallback
      • AccuracyCallback
      • CheckpointCallback
    • banhxeo.train.config module
      • LossConfig
      • OptimizerConfig
      • TrainerConfig
    • banhxeo.train.trainer module
      • Trainer
• banhxeo.utils package
  • RuntimeEnv
    • RuntimeEnv.JUPYTER
    • RuntimeEnv.SHELL
    • RuntimeEnv.IPYTHON
    • RuntimeEnv.COLAB
  • get_runtime()
  • Submodules
    • banhxeo.utils.file module
      • download_archive()
      • check_md5()
      • extract_archive()
    • banhxeo.utils.logging module
      • PrintLogger
      • Logger