Modules

• train_tokenizer module
  • add_vocab_from_file()
  • main()
  • Named Arguments
• create_config module
  • main()
  • Named Arguments
• tokenize_corpus module
  • main()
  • Named Arguments
• run_clm module
  • DataTrainingArguments
    • DataTrainingArguments.block_size
    • DataTrainingArguments.dataset_config_name
    • DataTrainingArguments.dataset_name
    • DataTrainingArguments.keep_linebreaks
    • DataTrainingArguments.line_by_line
    • DataTrainingArguments.max_eval_samples
    • DataTrainingArguments.max_seq_length
    • DataTrainingArguments.max_train_samples
    • DataTrainingArguments.overwrite_cache
    • DataTrainingArguments.pad_to_max_length
    • DataTrainingArguments.preprocessing_num_workers
    • DataTrainingArguments.test_file
    • DataTrainingArguments.train_file
    • DataTrainingArguments.validation_file
    • DataTrainingArguments.validation_split_percentage
  • ModelArguments
    • ModelArguments.cache_dir
    • ModelArguments.config_name
    • ModelArguments.config_overrides
    • ModelArguments.model_name_or_path
    • ModelArguments.model_revision
    • ModelArguments.model_type
    • ModelArguments.tokenizer_name
    • ModelArguments.use_auth_token
    • ModelArguments.use_fast_tokenizer
  • main()
• run_mlm module
  • DataTrainingArguments
    • DataTrainingArguments.dataset_config_name
    • DataTrainingArguments.dataset_name
    • DataTrainingArguments.keep_linebreaks
    • DataTrainingArguments.line_by_line
    • DataTrainingArguments.max_eval_samples
    • DataTrainingArguments.max_seq_length
    • DataTrainingArguments.max_train_samples
    • DataTrainingArguments.mlm_probability
    • DataTrainingArguments.overwrite_cache
    • DataTrainingArguments.pad_to_max_length
    • DataTrainingArguments.preprocessing_num_workers
    • DataTrainingArguments.test_file
    • DataTrainingArguments.train_file
    • DataTrainingArguments.validation_file
    • DataTrainingArguments.validation_split_percentage
  • ModelArguments
    • ModelArguments.cache_dir
    • ModelArguments.config_name
    • ModelArguments.config_overrides
    • ModelArguments.freeze_token_embed
    • ModelArguments.model_name_or_path
    • ModelArguments.model_revision
    • ModelArguments.model_type
    • ModelArguments.pretrained_token_embed
    • ModelArguments.tokenizer_name
    • ModelArguments.use_auth_token
    • ModelArguments.use_fast_tokenizer
  • main()
  • read_txt_embeddings()
• run_seq_to_seq_pretrain module
• run_tc module
  • DataTrainingArguments
    • DataTrainingArguments.dataset_config_name
    • DataTrainingArguments.dataset_name
    • DataTrainingArguments.early_stop
    • DataTrainingArguments.label_column_name
    • DataTrainingArguments.max_seq_length
    • DataTrainingArguments.overwrite_cache
    • DataTrainingArguments.pad_to_max_length
    • DataTrainingArguments.preprocessing_num_workers
    • DataTrainingArguments.task_name
    • DataTrainingArguments.test_file
    • DataTrainingArguments.text_column_name
    • DataTrainingArguments.train_file
    • DataTrainingArguments.validation_file
  • ModelArguments
    • ModelArguments.cache_dir
    • ModelArguments.config_name
    • ModelArguments.log_dir
    • ModelArguments.model_name_or_path
    • ModelArguments.tokenizer_name
    • ModelArguments.use_auth_token
    • ModelArguments.use_fast
  • main()
• run_seq module
  • DataTrainingArguments
    • DataTrainingArguments.dataset_config_name
    • DataTrainingArguments.dataset_name
    • DataTrainingArguments.max_eval_samples
    • DataTrainingArguments.max_predict_samples
    • DataTrainingArguments.max_seq_length
    • DataTrainingArguments.max_train_samples
    • DataTrainingArguments.overwrite_cache
    • DataTrainingArguments.pad_to_max_length
    • DataTrainingArguments.task_name
    • DataTrainingArguments.test_file
    • DataTrainingArguments.train_file
    • DataTrainingArguments.validation_file
  • ModelArguments
    • ModelArguments.cache_dir
    • ModelArguments.config_name
    • ModelArguments.log_dir
    • ModelArguments.model_name_or_path
    • ModelArguments.model_revision
    • ModelArguments.tokenizer_name
    • ModelArguments.use_auth_token
    • ModelArguments.use_fast_tokenizer
  • TaskArguments
    • TaskArguments.early_stop
    • TaskArguments.task
  • main()
• data_collator_for_seq_to_seq module