Index

_

__init__() (banhxeo.core.Vocabulary method) (banhxeo.core.vocabulary.Vocabulary method) (banhxeo.data.AmazonReviewFullDataset method) (banhxeo.data.base.BaseTextDataset method) (banhxeo.data.BaseTextDataset method) (banhxeo.data.config.DatasetSplit method) (banhxeo.data.config.DownloadDatasetFile method) (banhxeo.data.dataset.amazon_review.AmazonReviewFullDataset method) (banhxeo.data.dataset.imdb.IMDBDataset method) (banhxeo.data.IMDBDataset method) (banhxeo.data.torch.TorchTextDataset method) (banhxeo.data.transforms.ComposeTransforms method) (banhxeo.model.base.BaseLanguageModel method) (banhxeo.model.classic.gru.GRU method) (banhxeo.model.classic.gru.GRUCell method) (banhxeo.model.classic.lstm.LSTM method) (banhxeo.model.classic.lstm.LSTMCell method) (banhxeo.model.classic.mlp.MLP method) (banhxeo.model.classic.rnn.RNN method) (banhxeo.model.classic.rnn.RNNCell method) (banhxeo.model.classic.word2vec.Word2Vec method) (banhxeo.model.classic.word2vec.Word2VecDataset method) (banhxeo.model.llm.config.LayerNormConfig method) (banhxeo.model.llm.config.MHAConfig method) (banhxeo.model.llm.config.MLPConfig method) (banhxeo.model.llm.layers.layer_norm.LayerNorm method) (banhxeo.model.LSTM method) (banhxeo.model.MLP method) (banhxeo.model.neural.NeuralLanguageModel method) (banhxeo.model.NGram method) (banhxeo.model.old.n_gram.NGram method) (banhxeo.model.old.n_gram.NgramTrieNode method) (banhxeo.model.RNN method) (banhxeo.train.callbacks.AccuracyCallback method) (banhxeo.train.callbacks.CheckpointCallback method) (banhxeo.train.callbacks.ProgressCallback method) (banhxeo.train.trainer.Trainer method) (banhxeo.utils.logging.Logger method)

A

AccuracyCallback (class in banhxeo.train.callbacks) activation_fn (banhxeo.model.classic.mlp.MLPConfig attribute) add_special_tokens (banhxeo.core.tokenizer.TokenizerConfig attribute) (banhxeo.core.TokenizerConfig attribute) aggregate_strategy (banhxeo.model.classic.mlp.MLPConfig attribute)

AmazonReviewFullDataset (class in banhxeo.data) (class in banhxeo.data.dataset.amazon_review) arbitrary_types_allowed (banhxeo.data.config.TorchDatasetConfig.Config attribute) (banhxeo.train.config.OptimizerConfig.Config attribute) attach_downstream_head() (banhxeo.model.neural.NeuralLanguageModel method)

B

banhxeo module banhxeo.core module banhxeo.core.tokenizer module banhxeo.core.vocabulary module banhxeo.data module banhxeo.data.base module banhxeo.data.config module banhxeo.data.dataset module banhxeo.data.dataset.amazon_review module banhxeo.data.dataset.imdb module banhxeo.data.torch module banhxeo.data.transforms module banhxeo.model module banhxeo.model.base module banhxeo.model.classic module banhxeo.model.classic.gru module banhxeo.model.classic.lstm module banhxeo.model.classic.mlp module banhxeo.model.classic.rnn module banhxeo.model.classic.word2vec module banhxeo.model.config module banhxeo.model.llm module

banhxeo.model.llm.config module banhxeo.model.llm.gpt2 module banhxeo.model.llm.layers module banhxeo.model.llm.layers.layer_norm module banhxeo.model.neural module banhxeo.model.old module banhxeo.model.old.n_gram module banhxeo.train module banhxeo.train.callbacks module banhxeo.train.config module banhxeo.train.trainer module banhxeo.utils module banhxeo.utils.file module banhxeo.utils.logging module BaseLanguageModel (class in banhxeo.model.base) BaseTextDataset (class in banhxeo.data) (class in banhxeo.data.base) batch_encode() (banhxeo.core.Tokenizer method) (banhxeo.core.tokenizer.Tokenizer method) bias (banhxeo.model.classic.rnn.RNNConfig attribute) (banhxeo.model.llm.config.LayerNormConfig attribute) bidirectional (banhxeo.model.classic.rnn.RNNConfig attribute) bos_id (banhxeo.core.Vocabulary property) (banhxeo.core.vocabulary.Vocabulary property) bos_tok (banhxeo.core.VocabConfig attribute) (banhxeo.core.vocabulary.VocabConfig attribute) bos_toks (banhxeo.core.Vocabulary property) (banhxeo.core.vocabulary.Vocabulary property) build() (banhxeo.core.Vocabulary class method) (banhxeo.core.vocabulary.Vocabulary class method)

C

check_and_raise() (banhxeo.utils.logging.Logger method) check_config() (banhxeo.model.classic.rnn.RNNConfig method) check_grad_acc_steps() (banhxeo.train.config.TrainerConfig class method) check_md5() (in module banhxeo.utils.file) check_min_freq_positive() (banhxeo.core.VocabConfig class method) (banhxeo.core.vocabulary.VocabConfig class method) check_n() (banhxeo.model.old.n_gram.NGramConfig method) check_padding() (banhxeo.core.tokenizer.TokenizerConfig method) (banhxeo.core.TokenizerConfig method) check_smoothing() (banhxeo.model.old.n_gram.NGramConfig method) check_valid() (banhxeo.model.classic.mlp.MLPConfig method)

CheckpointCallback (class in banhxeo.train.callbacks) children (banhxeo.model.old.n_gram.NgramTrieNode attribute) cls_tok (banhxeo.core.VocabConfig attribute) (banhxeo.core.vocabulary.VocabConfig attribute) COLAB (banhxeo.utils.RuntimeEnv attribute) ComposeTransforms (class in banhxeo.data.transforms) ConfigClass (banhxeo.model.classic.mlp.MLP attribute) (banhxeo.model.MLP attribute) (banhxeo.model.NGram attribute) (banhxeo.model.old.n_gram.NGram attribute) count (banhxeo.model.old.n_gram.NgramTrieNode attribute)

D

d_model (banhxeo.model.llm.config.GPT2Config attribute) DatasetConfig (class in banhxeo.data.config) DatasetSplit (class in banhxeo.data.config) debug (banhxeo.model.llm.config.GPT2Config attribute) debug() (banhxeo.utils.logging.Logger method) (banhxeo.utils.logging.PrintLogger method) detokenize() (banhxeo.core.NLTKTokenizer method) (banhxeo.core.tokenizer.NLTKTokenizer method)

dim (banhxeo.model.llm.config.MHAConfig attribute) (banhxeo.model.llm.config.MLPConfig attribute) download_archive() (in module banhxeo.utils.file) DownloadDatasetFile (class in banhxeo.data.config) dropout (banhxeo.model.classic.rnn.RNNConfig attribute) dropout_rate (banhxeo.model.classic.mlp.MLPConfig attribute)

E

elementwise_affine (banhxeo.model.llm.config.LayerNormConfig attribute) embedding_dim (banhxeo.model.neural.NeuralModelConfig attribute) encode() (banhxeo.core.Tokenizer method) (banhxeo.core.tokenizer.Tokenizer method) ensure_compose_transforms() (banhxeo.data.config.TorchDatasetConfig class method) eps (banhxeo.model.llm.config.LayerNormConfig attribute) error() (banhxeo.utils.logging.Logger method) (banhxeo.utils.logging.PrintLogger method)

evaluate() (banhxeo.train.trainer.Trainer method) evaluate_during_training (banhxeo.train.config.TrainerConfig attribute) evaluation_steps (banhxeo.train.config.TrainerConfig attribute) exception() (banhxeo.utils.logging.Logger method) (banhxeo.utils.logging.PrintLogger method) ext (banhxeo.data.config.DownloadDatasetFile attribute) extract_archive() (in module banhxeo.utils.file)

F

file_info (banhxeo.data.config.DatasetConfig attribute) fit() (banhxeo.model.NGram method) (banhxeo.model.old.n_gram.NGram method) forward() (banhxeo.model.classic.gru.GRU method) (banhxeo.model.classic.gru.GRUCell method) (banhxeo.model.classic.lstm.LSTM method) (banhxeo.model.classic.lstm.LSTMCell method) (banhxeo.model.classic.mlp.MLP method) (banhxeo.model.classic.rnn.RNN method) (banhxeo.model.classic.rnn.RNNCell method) (banhxeo.model.classic.word2vec.Word2Vec method) (banhxeo.model.llm.layers.layer_norm.LayerNorm method) (banhxeo.model.LSTM method) (banhxeo.model.MLP method) (banhxeo.model.neural.NeuralLanguageModel method) (banhxeo.model.RNN method)

freeze() (banhxeo.model.neural.NeuralLanguageModel method) from_pretrained() (banhxeo.core.Tokenizer class method) (banhxeo.core.tokenizer.Tokenizer class method)

G

generate_sequence() (banhxeo.model.classic.mlp.MLP method) (banhxeo.model.MLP method) (banhxeo.model.neural.NeuralLanguageModel method) (banhxeo.model.NGram method) (banhxeo.model.old.n_gram.NGram method) GenerateConfig (class in banhxeo.model.config) get_all_texts() (banhxeo.data.base.BaseTextDataset method) (banhxeo.data.BaseTextDataset method) get_callbacks_output() (banhxeo.train.trainer.Trainer method) get_config() (banhxeo.model.base.BaseLanguageModel method) get_data() (banhxeo.data.base.BaseTextDataset method) (banhxeo.data.BaseTextDataset method) get_downstream_head_output() (banhxeo.model.neural.NeuralLanguageModel method) get_eval_dataloader() (banhxeo.train.trainer.Trainer method) get_loss_function() (banhxeo.train.config.LossConfig method)

get_optimizer() (banhxeo.train.config.OptimizerConfig method) get_output() (banhxeo.train.callbacks.AccuracyCallback method) (banhxeo.train.callbacks.TrainerCallback method) get_runtime() (in module banhxeo.utils) get_scheduler() (banhxeo.train.config.OptimizerConfig method) get_train_dataloader() (banhxeo.train.trainer.Trainer method) get_vocab() (banhxeo.core.Vocabulary method) (banhxeo.core.vocabulary.Vocabulary method) get_word_counts() (banhxeo.core.Vocabulary method) (banhxeo.core.vocabulary.Vocabulary method) GPT2Config (class in banhxeo.model.llm.config) gradient_accumulation_steps (banhxeo.train.config.TrainerConfig attribute) GRU (class in banhxeo.model.classic.gru) GRUCell (class in banhxeo.model.classic.gru) GRUConfig (class in banhxeo.model.classic.gru)

H

hf_name (banhxeo.data.config.DatasetConfig attribute) hf_path (banhxeo.data.config.DatasetConfig attribute)

hidden_size (banhxeo.model.classic.rnn.RNNConfig attribute) hidden_sizes (banhxeo.model.classic.mlp.MLPConfig attribute)

I

id (banhxeo.model.old.n_gram.NgramTrieNode attribute) ids_to_tokens() (banhxeo.core.Vocabulary method) (banhxeo.core.vocabulary.Vocabulary method) idx_to_token (banhxeo.core.Vocabulary property) (banhxeo.core.vocabulary.Vocabulary property) IMDBDataset (class in banhxeo.data) (class in banhxeo.data.dataset.imdb)

info() (banhxeo.utils.logging.Logger method) (banhxeo.utils.logging.PrintLogger method) init_range (banhxeo.model.llm.config.GPT2Config attribute) inspect_huggingface_dataset() (banhxeo.data.base.BaseTextDataset static method) (banhxeo.data.BaseTextDataset static method) IPYTHON (banhxeo.utils.RuntimeEnv attribute) is_classification (banhxeo.data.config.TorchDatasetConfig attribute) is_end_of_ngram (banhxeo.model.old.n_gram.NgramTrieNode attribute)

J

JUPYTER (banhxeo.utils.RuntimeEnv attribute)

K

k (banhxeo.model.config.GenerateConfig attribute) (banhxeo.model.old.n_gram.NGramConfig attribute)

kwargs (banhxeo.train.config.LossConfig attribute)

L

label_column (banhxeo.data.config.DatasetConfig attribute) label_column_name (banhxeo.data.config.TorchDatasetConfig attribute) label_map (banhxeo.data.config.DatasetConfig attribute) (banhxeo.data.config.TorchDatasetConfig attribute) LayerNorm (class in banhxeo.model.llm.layers.layer_norm) LayerNormConfig (class in banhxeo.model.llm.config) ln (banhxeo.model.llm.config.GPT2Config attribute) load() (banhxeo.core.Vocabulary class method) (banhxeo.core.vocabulary.Vocabulary class method) load_from_huggingface() (banhxeo.data.base.BaseTextDataset class method) (banhxeo.data.BaseTextDataset class method)

load_model() (banhxeo.model.base.BaseLanguageModel class method) (banhxeo.model.neural.NeuralLanguageModel class method) Logger (class in banhxeo.utils.logging) logging_steps (banhxeo.train.config.TrainerConfig attribute) loss (banhxeo.train.config.TrainerConfig attribute) LossConfig (class in banhxeo.train.config) lr_scheduler_kwargs (banhxeo.train.config.OptimizerConfig attribute) LSTM (class in banhxeo.model) (class in banhxeo.model.classic.lstm) LSTMCell (class in banhxeo.model.classic.lstm) LSTMConfig (class in banhxeo.model.classic.lstm)

M

mask_tok (banhxeo.core.VocabConfig attribute) (banhxeo.core.vocabulary.VocabConfig attribute) max_length (banhxeo.core.tokenizer.TokenizerConfig attribute) (banhxeo.core.TokenizerConfig attribute) (banhxeo.model.config.GenerateConfig attribute) md5 (banhxeo.data.config.DatasetConfig attribute) metadata (banhxeo.data.transforms.Transforms attribute) mha (banhxeo.model.llm.config.GPT2Config attribute) MHAConfig (class in banhxeo.model.llm.config) min_freq (banhxeo.core.VocabConfig attribute) (banhxeo.core.vocabulary.VocabConfig attribute) mlp (banhxeo.model.llm.config.GPT2Config attribute) MLP (class in banhxeo.model) (class in banhxeo.model.classic.mlp) MLPConfig (class in banhxeo.model.classic.mlp) (class in banhxeo.model.llm.config) model_config (banhxeo.core.tokenizer.TokenizerConfig attribute) (banhxeo.core.TokenizerConfig attribute) (banhxeo.core.VocabConfig attribute) (banhxeo.core.vocabulary.VocabConfig attribute) (banhxeo.data.config.DatasetConfig attribute) (banhxeo.data.config.TorchDatasetConfig attribute) (banhxeo.data.transforms.RemoveHTMLTag attribute) (banhxeo.data.transforms.RemovePunctuation attribute) (banhxeo.data.transforms.RemoveURL attribute) (banhxeo.data.transforms.SpellingCorrection attribute) (banhxeo.data.transforms.Strip attribute) (banhxeo.data.transforms.Transforms attribute) (banhxeo.model.classic.gru.GRUConfig attribute) (banhxeo.model.classic.lstm.LSTMConfig attribute) (banhxeo.model.classic.mlp.MLPConfig attribute) (banhxeo.model.classic.rnn.RNNConfig attribute) (banhxeo.model.config.GenerateConfig attribute) (banhxeo.model.config.ModelConfig attribute) (banhxeo.model.llm.config.GPT2Config attribute) (banhxeo.model.neural.NeuralModelConfig attribute) (banhxeo.model.old.n_gram.NGramConfig attribute) (banhxeo.train.config.LossConfig attribute) (banhxeo.train.config.OptimizerConfig attribute) (banhxeo.train.config.TrainerConfig attribute)

ModelConfig (class in banhxeo.model.config) module banhxeo banhxeo.core banhxeo.core.tokenizer banhxeo.core.vocabulary banhxeo.data banhxeo.data.base banhxeo.data.config banhxeo.data.dataset banhxeo.data.dataset.amazon_review banhxeo.data.dataset.imdb banhxeo.data.torch banhxeo.data.transforms banhxeo.model banhxeo.model.base banhxeo.model.classic banhxeo.model.classic.gru banhxeo.model.classic.lstm banhxeo.model.classic.mlp banhxeo.model.classic.rnn banhxeo.model.classic.word2vec banhxeo.model.config banhxeo.model.llm banhxeo.model.llm.config banhxeo.model.llm.gpt2 banhxeo.model.llm.layers banhxeo.model.llm.layers.layer_norm banhxeo.model.neural banhxeo.model.old banhxeo.model.old.n_gram banhxeo.train banhxeo.train.callbacks banhxeo.train.config banhxeo.train.trainer banhxeo.utils banhxeo.utils.file banhxeo.utils.logging

N

n (banhxeo.model.old.n_gram.NGramConfig attribute) n_ctx (banhxeo.model.llm.config.GPT2Config attribute) n_heads (banhxeo.model.llm.config.MHAConfig attribute) n_layers (banhxeo.model.llm.config.GPT2Config attribute) name (banhxeo.data.config.DatasetConfig attribute) (banhxeo.data.config.DownloadDatasetFile attribute) (banhxeo.train.callbacks.AccuracyCallback attribute) (banhxeo.train.callbacks.CheckpointCallback attribute) (banhxeo.train.callbacks.ProgressCallback attribute) (banhxeo.train.callbacks.TrainerCallback attribute) (banhxeo.train.config.LossConfig attribute) (banhxeo.train.config.OptimizerConfig attribute)

NeuralLanguageModel (class in banhxeo.model.neural) NeuralModelConfig (class in banhxeo.model.neural) NGram (class in banhxeo.model) (class in banhxeo.model.old.n_gram) NGramConfig (class in banhxeo.model.old.n_gram) NgramTrieNode (class in banhxeo.model.old.n_gram) NLTKTokenizer (class in banhxeo.core) (class in banhxeo.core.tokenizer) num_layers (banhxeo.model.classic.rnn.RNNConfig attribute) num_train_epochs (banhxeo.train.config.TrainerConfig attribute)

O

on_epoch_begin() (banhxeo.train.callbacks.ProgressCallback method) (banhxeo.train.callbacks.TrainerCallback method) on_epoch_end() (banhxeo.train.callbacks.CheckpointCallback method) (banhxeo.train.callbacks.TrainerCallback method) on_evaluate() (banhxeo.train.callbacks.AccuracyCallback method) (banhxeo.train.callbacks.TrainerCallback method) on_init_end() (banhxeo.train.callbacks.TrainerCallback method) on_save() (banhxeo.train.callbacks.TrainerCallback method) on_step_begin() (banhxeo.train.callbacks.TrainerCallback method) on_step_end() (banhxeo.train.callbacks.AccuracyCallback method) (banhxeo.train.callbacks.CheckpointCallback method) (banhxeo.train.callbacks.ProgressCallback method) (banhxeo.train.callbacks.TrainerCallback method)

on_train_begin() (banhxeo.train.callbacks.ProgressCallback method) (banhxeo.train.callbacks.TrainerCallback method) on_train_end() (banhxeo.train.callbacks.ProgressCallback method) (banhxeo.train.callbacks.TrainerCallback method) optim (banhxeo.train.config.TrainerConfig attribute) optimizer_kwargs (banhxeo.train.config.OptimizerConfig attribute) OptimizerConfig (class in banhxeo.train.config) OptimizerConfig.Config (class in banhxeo.train.config) output_dir (banhxeo.train.config.TrainerConfig attribute) output_size (banhxeo.model.classic.mlp.MLPConfig attribute)

P

p (banhxeo.model.config.GenerateConfig attribute) pad_id (banhxeo.core.Vocabulary property) (banhxeo.core.vocabulary.Vocabulary property) pad_tok (banhxeo.core.VocabConfig attribute) (banhxeo.core.vocabulary.VocabConfig attribute) padding (banhxeo.core.tokenizer.TokenizerConfig attribute) (banhxeo.core.TokenizerConfig attribute)

per_device_eval_batch_size (banhxeo.train.config.TrainerConfig attribute) per_device_train_batch_size (banhxeo.train.config.TrainerConfig attribute) prepare_data() (banhxeo.model.classic.word2vec.Word2Vec static method) PrintLogger (class in banhxeo.utils.logging) ProgressCallback (class in banhxeo.train.callbacks)

R

RemoveHTMLTag (class in banhxeo.data.transforms) RemovePunctuation (class in banhxeo.data.transforms) RemoveURL (class in banhxeo.data.transforms) resv_tok (banhxeo.core.VocabConfig attribute) (banhxeo.core.vocabulary.VocabConfig attribute)

RNN (class in banhxeo.model) (class in banhxeo.model.classic.rnn) RNNCell (class in banhxeo.model.classic.rnn) RNNConfig (class in banhxeo.model.classic.rnn) RuntimeEnv (class in banhxeo.utils)

S

sampling (banhxeo.model.config.GenerateConfig attribute) save() (banhxeo.core.Vocabulary method) (banhxeo.core.vocabulary.Vocabulary method) save_model() (banhxeo.model.base.BaseLanguageModel method) (banhxeo.model.neural.NeuralLanguageModel method) (banhxeo.train.trainer.Trainer method) save_pretrained() (banhxeo.core.Tokenizer method) (banhxeo.core.tokenizer.Tokenizer method) save_steps (banhxeo.train.config.TrainerConfig attribute) save_total_limit (banhxeo.train.config.TrainerConfig attribute) scheduler_name (banhxeo.train.config.OptimizerConfig attribute) seed (banhxeo.train.config.TrainerConfig attribute) sep (banhxeo.core.Vocabulary property) (banhxeo.core.vocabulary.Vocabulary property) sep_id (banhxeo.core.Vocabulary property) (banhxeo.core.vocabulary.Vocabulary property)

sep_tok (banhxeo.core.VocabConfig attribute) (banhxeo.core.vocabulary.VocabConfig attribute) sep_toks (banhxeo.core.Vocabulary property) (banhxeo.core.vocabulary.Vocabulary property) set_default_gpu() (in module banhxeo) SHELL (banhxeo.utils.RuntimeEnv attribute) smoothing (banhxeo.model.old.n_gram.NGramConfig attribute) source (banhxeo.data.config.DownloadDatasetFile attribute) special_token_idx() (banhxeo.core.VocabConfig method) (banhxeo.core.vocabulary.VocabConfig method) special_tokens (banhxeo.core.VocabConfig property) (banhxeo.core.vocabulary.VocabConfig property) SpellingCorrection (class in banhxeo.data.transforms) split (banhxeo.data.config.DatasetConfig attribute) Strip (class in banhxeo.data.transforms) summary() (banhxeo.model.base.BaseLanguageModel method) (banhxeo.model.neural.NeuralLanguageModel method)

T

temp (banhxeo.model.config.GenerateConfig attribute) template (banhxeo.utils.logging.PrintLogger attribute) test (banhxeo.data.config.DatasetSplit attribute) text_column (banhxeo.data.config.DatasetConfig attribute) text_column_name (banhxeo.data.config.TorchDatasetConfig attribute) to_cpu() (banhxeo.model.neural.NeuralLanguageModel method) to_gpu() (banhxeo.model.neural.NeuralLanguageModel method) to_loader() (banhxeo.data.torch.TorchTextDataset method) to_torch_dataset() (banhxeo.data.base.BaseTextDataset method) (banhxeo.data.BaseTextDataset method) token_to_idx (banhxeo.core.Vocabulary property) (banhxeo.core.vocabulary.Vocabulary property) tokenize() (banhxeo.core.NLTKTokenizer method) (banhxeo.core.Tokenizer method) (banhxeo.core.tokenizer.NLTKTokenizer method) (banhxeo.core.tokenizer.Tokenizer method) tokenizer (banhxeo.data.config.TorchDatasetConfig attribute) Tokenizer (class in banhxeo.core) (class in banhxeo.core.tokenizer)

tokenizer_config (banhxeo.data.config.TorchDatasetConfig attribute) TokenizerConfig (class in banhxeo.core) (class in banhxeo.core.tokenizer) tokens_to_ids() (banhxeo.core.Vocabulary method) (banhxeo.core.vocabulary.Vocabulary method) TorchDatasetConfig (class in banhxeo.data.config) TorchDatasetConfig.Config (class in banhxeo.data.config) TorchTextDataset (class in banhxeo.data.torch) train (banhxeo.data.config.DatasetSplit attribute) train() (banhxeo.train.trainer.Trainer method) train_from_iterator() (banhxeo.core.Tokenizer method) (banhxeo.core.tokenizer.Tokenizer method) Trainer (class in banhxeo.train.trainer) TrainerCallback (class in banhxeo.train.callbacks) TrainerConfig (class in banhxeo.train.config) training_shuffle (banhxeo.train.config.TrainerConfig attribute) transforms (banhxeo.data.config.TorchDatasetConfig attribute) Transforms (class in banhxeo.data.transforms) truncation (banhxeo.core.tokenizer.TokenizerConfig attribute) (banhxeo.core.TokenizerConfig attribute)

U

unfreeze() (banhxeo.model.neural.NeuralLanguageModel method) unk_id (banhxeo.core.Vocabulary property) (banhxeo.core.vocabulary.Vocabulary property) unk_tok (banhxeo.core.VocabConfig attribute) (banhxeo.core.Vocabulary property) (banhxeo.core.vocabulary.VocabConfig attribute) (banhxeo.core.vocabulary.Vocabulary property)

url (banhxeo.data.config.DatasetConfig attribute)

V

val (banhxeo.data.config.DatasetSplit attribute) vocab (banhxeo.data.config.TorchDatasetConfig attribute) vocab_size (banhxeo.core.Vocabulary property) (banhxeo.core.vocabulary.Vocabulary property) (banhxeo.model.config.ModelConfig attribute)

VocabConfig (class in banhxeo.core) (class in banhxeo.core.vocabulary) Vocabulary (class in banhxeo.core) (class in banhxeo.core.vocabulary)

W

warning() (banhxeo.utils.logging.Logger method) (banhxeo.utils.logging.PrintLogger method)

window_size (banhxeo.model.classic.mlp.MLPConfig attribute) Word2Vec (class in banhxeo.model.classic.word2vec) Word2VecDataset (class in banhxeo.model.classic.word2vec)