transformers4rec.config package

Submodules

transformers4rec.config.schema module

class transformers4rec.config.schema.SchemaMixin

Bases: object

REQUIRES_SCHEMA = False

set_schema(schema=None)

property schema

check_schema(schema=None)

get_item_ids_from_inputs(inputs)

get_padding_mask_from_item_id(inputs, pad_token=0)

transformers4rec.config.schema.requires_schema(module)

transformers4rec.config.trainer module

class transformers4rec.config.trainer.T4RecTrainingArguments(output_dir: str, overwrite_output_dir: bool = False, do_train: bool = False, do_eval: bool = False, do_predict: bool = False, evaluation_strategy: Union[transformers.trainer_utils.IntervalStrategy, str] = 'no', prediction_loss_only: bool = False, per_device_train_batch_size: int = 8, per_device_eval_batch_size: int = 8, per_gpu_train_batch_size: Optional[int] = None, per_gpu_eval_batch_size: Optional[int] = None, gradient_accumulation_steps: int = 1, eval_accumulation_steps: Optional[int] = None, eval_delay: Optional[float] = 0, learning_rate: float = 5e-05, weight_decay: float = 0.0, adam_beta1: float = 0.9, adam_beta2: float = 0.999, adam_epsilon: float = 1e-08, max_grad_norm: float = 1.0, num_train_epochs: float = 3.0, max_steps: int = - 1, lr_scheduler_type: Union[transformers.trainer_utils.SchedulerType, str] = 'linear', warmup_ratio: float = 0.0, warmup_steps: int = 0, log_level: Optional[str] = 'passive', log_level_replica: Optional[str] = 'warning', log_on_each_node: bool = True, logging_dir: Optional[str] = None, logging_strategy: Union[transformers.trainer_utils.IntervalStrategy, str] = 'steps', logging_first_step: bool = False, logging_steps: float = 500, logging_nan_inf_filter: bool = True, save_strategy: Union[transformers.trainer_utils.IntervalStrategy, str] = 'steps', save_steps: float = 500, save_total_limit: Optional[int] = None, save_safetensors: Optional[bool] = False, save_on_each_node: bool = False, no_cuda: bool = False, use_mps_device: bool = False, seed: int = 42, data_seed: Optional[int] = None, jit_mode_eval: bool = False, use_ipex: bool = False, bf16: bool = False, fp16: bool = False, fp16_opt_level: str = 'O1', half_precision_backend: str = 'auto', bf16_full_eval: bool = False, fp16_full_eval: bool = False, tf32: Optional[bool] = None, local_rank: int = - 1, ddp_backend: Optional[str] = None, tpu_num_cores: Optional[int] = None, tpu_metrics_debug: bool = False, debug: str = '', dataloader_drop_last: bool = False, eval_steps: Optional[float] = None, dataloader_num_workers: int = 0, past_index: int = - 1, run_name: Optional[str] = None, disable_tqdm: Optional[bool] = None, remove_unused_columns: Optional[bool] = True, label_names: Optional[List[str]] = None, load_best_model_at_end: Optional[bool] = False, metric_for_best_model: Optional[str] = None, greater_is_better: Optional[bool] = None, ignore_data_skip: bool = False, sharded_ddp: str = '', fsdp: str = '', fsdp_min_num_params: int = 0, fsdp_config: Optional[str] = None, fsdp_transformer_layer_cls_to_wrap: Optional[str] = None, deepspeed: Optional[str] = None, label_smoothing_factor: float = 0.0, optim: Union[transformers.training_args.OptimizerNames, str] = 'adamw_hf', optim_args: Optional[str] = None, adafactor: bool = False, group_by_length: bool = False, length_column_name: Optional[str] = 'length', report_to: Optional[List[str]] = None, ddp_find_unused_parameters: Optional[bool] = None, ddp_bucket_cap_mb: Optional[int] = None, dataloader_pin_memory: bool = True, skip_memory_metrics: bool = True, use_legacy_prediction_loop: bool = False, push_to_hub: bool = False, resume_from_checkpoint: Optional[str] = None, hub_model_id: Optional[str] = None, hub_strategy: Union[transformers.trainer_utils.HubStrategy, str] = 'every_save', hub_token: Optional[str] = None, hub_private_repo: bool = False, gradient_checkpointing: bool = False, include_inputs_for_metrics: bool = False, fp16_backend: str = 'auto', push_to_hub_model_id: Optional[str] = None, push_to_hub_organization: Optional[str] = None, push_to_hub_token: Optional[str] = None, mp_parameters: str = '', auto_find_batch_size: bool = False, full_determinism: bool = False, torchdynamo: Optional[str] = None, ray_scope: Optional[str] = 'last', ddp_timeout: Optional[int] = 1800, torch_compile: bool = False, torch_compile_backend: Optional[str] = None, torch_compile_mode: Optional[str] = None, xpu_backend: Optional[str] = None, max_sequence_length: Optional[int] = None, shuffle_buffer_size: int = 0, data_loader_engine: str = 'merlin', eval_on_test_set: bool = False, eval_steps_on_train_set: int = 20, predict_top_k: int = 100, learning_rate_num_cosine_cycles_by_epoch: float = 1.25, log_predictions: bool = False, compute_metrics_each_n_steps: int = 1, experiments_group: str = 'default')

Bases: transformers.training_args.TrainingArguments

Class that inherits HF TrainingArguments and add on top of it arguments needed for session-based and sequential-based recommendation

Parameters

• shuffle_buffer_size (int) –

• validate_every (Optional[int], int) – Run validation set every this epoch. -1 means no validation is used by default -1

• eval_on_test_set (bool) –

• eval_steps_on_train_set (int) –

• predict_top_k (Option[int], int) – Truncate recommendation list to the highest top-K predicted items, (do not affect evaluation metrics computation), This parameter is specific to NextItemPredictionTask and only affects model.predict() and model.evaluate(), which both call Trainer.evaluation_loop. By default 100.

• log_predictions (Optional[bool], bool) – log predictions, labels and metadata features each –compute_metrics_each_n_steps (for test set). by default False

• log_attention_weights (Optional[bool], bool) – Logs the inputs and attention weights each –eval_steps (only test set)” by default False

• learning_rate_num_cosine_cycles_by_epoch (Optional[int], int) – Number of cycles for by epoch when –lr_scheduler_type = cosine_with_warmup. The number of waves in the cosine schedule (e.g. 0.5 is to just decrease from the max value to 0, following a half-cosine). by default 1.25

• experiments_group (Optional[str], str) – Name of the Experiments Group, for organizing job runs logged on W&B by default “default”

max_sequence_length: Optional[int] = None

shuffle_buffer_size: int = 0

data_loader_engine: str = 'merlin'

eval_on_test_set: bool = False

eval_steps_on_train_set: int = 20

predict_top_k: int = 100

learning_rate_num_cosine_cycles_by_epoch: float = 1.25

log_predictions: bool = False

compute_metrics_each_n_steps: int = 1

experiments_group: str = 'default'

property place_model_on_device

Override the method to allow running training on cpu

class transformers4rec.config.trainer.T4RecTrainingArgumentsTF(output_dir: str, overwrite_output_dir: bool = False, do_train: bool = False, do_eval: bool = False, do_predict: bool = False, evaluation_strategy: Union[transformers.trainer_utils.IntervalStrategy, str] = 'no', prediction_loss_only: bool = False, per_device_train_batch_size: int = 8, per_device_eval_batch_size: int = 8, per_gpu_train_batch_size: Optional[int] = None, per_gpu_eval_batch_size: Optional[int] = None, gradient_accumulation_steps: int = 1, eval_accumulation_steps: Optional[int] = None, eval_delay: Optional[float] = 0, learning_rate: float = 5e-05, weight_decay: float = 0.0, adam_beta1: float = 0.9, adam_beta2: float = 0.999, adam_epsilon: float = 1e-08, max_grad_norm: float = 1.0, num_train_epochs: float = 3.0, max_steps: int = - 1, lr_scheduler_type: Union[transformers.trainer_utils.SchedulerType, str] = 'linear', warmup_ratio: float = 0.0, warmup_steps: int = 0, log_level: Optional[str] = 'passive', log_level_replica: Optional[str] = 'warning', log_on_each_node: bool = True, logging_dir: Optional[str] = None, logging_strategy: Union[transformers.trainer_utils.IntervalStrategy, str] = 'steps', logging_first_step: bool = False, logging_steps: float = 500, logging_nan_inf_filter: bool = True, save_strategy: Union[transformers.trainer_utils.IntervalStrategy, str] = 'steps', save_steps: float = 500, save_total_limit: Optional[int] = None, save_safetensors: Optional[bool] = False, save_on_each_node: bool = False, no_cuda: bool = False, use_mps_device: bool = False, seed: int = 42, data_seed: Optional[int] = None, jit_mode_eval: bool = False, use_ipex: bool = False, bf16: bool = False, fp16: bool = False, fp16_opt_level: str = 'O1', half_precision_backend: str = 'auto', bf16_full_eval: bool = False, fp16_full_eval: bool = False, tf32: Optional[bool] = None, local_rank: int = - 1, ddp_backend: Optional[str] = None, tpu_num_cores: Optional[int] = None, tpu_metrics_debug: bool = False, debug: str = '', dataloader_drop_last: bool = False, eval_steps: Optional[float] = None, dataloader_num_workers: int = 0, past_index: int = - 1, run_name: Optional[str] = None, disable_tqdm: Optional[bool] = None, remove_unused_columns: Optional[bool] = True, label_names: Optional[List[str]] = None, load_best_model_at_end: Optional[bool] = False, metric_for_best_model: Optional[str] = None, greater_is_better: Optional[bool] = None, ignore_data_skip: bool = False, sharded_ddp: str = '', fsdp: str = '', fsdp_min_num_params: int = 0, fsdp_config: Optional[str] = None, fsdp_transformer_layer_cls_to_wrap: Optional[str] = None, deepspeed: Optional[str] = None, label_smoothing_factor: float = 0.0, optim: Union[transformers.training_args.OptimizerNames, str] = 'adamw_hf', optim_args: Optional[str] = None, adafactor: bool = False, group_by_length: bool = False, length_column_name: Optional[str] = 'length', report_to: Optional[List[str]] = None, ddp_find_unused_parameters: Optional[bool] = None, ddp_bucket_cap_mb: Optional[int] = None, dataloader_pin_memory: bool = True, skip_memory_metrics: bool = True, use_legacy_prediction_loop: bool = False, push_to_hub: bool = False, resume_from_checkpoint: Optional[str] = None, hub_model_id: Optional[str] = None, hub_strategy: Union[transformers.trainer_utils.HubStrategy, str] = 'every_save', hub_token: Optional[str] = None, hub_private_repo: bool = False, gradient_checkpointing: bool = False, include_inputs_for_metrics: bool = False, fp16_backend: str = 'auto', push_to_hub_model_id: Optional[str] = None, push_to_hub_organization: Optional[str] = None, push_to_hub_token: Optional[str] = None, mp_parameters: str = '', auto_find_batch_size: bool = False, full_determinism: bool = False, torchdynamo: Optional[str] = None, ray_scope: Optional[str] = 'last', ddp_timeout: Optional[int] = 1800, torch_compile: bool = False, torch_compile_backend: Optional[str] = None, torch_compile_mode: Optional[str] = None, xpu_backend: Optional[str] = None, max_sequence_length: Optional[int] = None, shuffle_buffer_size: int = 0, data_loader_engine: str = 'merlin', eval_on_test_set: bool = False, eval_steps_on_train_set: int = 20, predict_top_k: int = 100, learning_rate_num_cosine_cycles_by_epoch: float = 1.25, log_predictions: bool = False, compute_metrics_each_n_steps: int = 1, experiments_group: str = 'default')

Bases: transformers4rec.config.trainer.T4RecTrainingArguments, transformers.training_args_tf.TFTrainingArguments

Prepare Training arguments for TFTrainer, Inherit arguments from T4RecTrainingArguments and TFTrainingArguments

output_dir: str

transformers4rec.config.transformer module

class transformers4rec.config.transformer.T4RecConfig

Bases: object

A class responsible for setting the configuration of the transformers class from Hugging Face and returning the corresponding T4Rec model.

to_huggingface_torch_model()

Instantiate a Hugging Face transformer model based on the configuration parameters of the class.

Returns

The Hugging Face transformer model.

Return type

transformers.PreTrainedModel

to_torch_model(input_features, *prediction_task, task_blocks=None, task_weights=None, loss_reduction='mean', **kwargs)

Links the Hugging Face transformer model to the given input block and prediction tasks, and returns a T4Rec model.

Parameters

• input_features (torch4rec.TabularSequenceFeatures) – The sequential block that represents the input features and defines the masking strategy for training and evaluation.

• prediction_task (torch4rec.PredictionTask) – One or multiple prediction tasks.

• task_blocks (list, optional) – List of task-specific blocks that we apply on top of the HF transformer’s output.

• task_weights (list, optional) – List of the weights to use for combining the tasks losses.

• loss_reduction (str, optional) –

  The reduction to apply to the prediction losses, possible values are:

  ’none’: no reduction will be applied, ‘mean’: the weighted mean of the output is taken, ‘sum’: the output will be summed.

  By default: ‘mean’.

Returns

The T4Rec torch model.

Return type

torch4rec.Model

Raises

ValueError – If input block or prediction task is of the wrong type.

property transformers_config_cls

classmethod build(*args, **kwargs)

class transformers4rec.config.transformer.ReformerConfig(attention_head_size=64, attn_layers=['local', 'lsh', 'local', 'lsh', 'local', 'lsh'], axial_norm_std=1.0, axial_pos_embds=True, axial_pos_shape=[64, 64], axial_pos_embds_dim=[64, 192], chunk_size_lm_head=0, eos_token_id=2, feed_forward_size=512, hash_seed=None, hidden_act='relu', hidden_dropout_prob=0.05, hidden_size=256, initializer_range=0.02, is_decoder=False, layer_norm_eps=1e-12, local_num_chunks_before=1, local_num_chunks_after=0, local_attention_probs_dropout_prob=0.05, local_attn_chunk_length=64, lsh_attn_chunk_length=64, lsh_attention_probs_dropout_prob=0.0, lsh_num_chunks_before=1, lsh_num_chunks_after=0, max_position_embeddings=4096, num_attention_heads=12, num_buckets=None, num_hashes=1, pad_token_id=0, vocab_size=320, tie_word_embeddings=False, use_cache=True, classifier_dropout=None, **kwargs)

Bases: transformers4rec.config.transformer.T4RecConfig, transformers.models.reformer.configuration_reformer.ReformerConfig

Subclass of T4RecConfig and transformers.ReformerConfig from Hugging Face. It handles configuration for Reformer layers in the context of T4Rec models.

classmethod build(d_model, n_head, n_layer, total_seq_length, hidden_act='gelu', initializer_range=0.01, layer_norm_eps=0.03, dropout=0.3, pad_token=0, log_attention_weights=False, axial_pos_shape_first_dim=4, **kwargs)

Creates an instance of ReformerConfig with the given parameters.

Parameters

• {transformer_cfg_parameters} –

• axial_pos_shape_first_dim (int, optional) – The first dimension of the axial position encodings. During training, the product of the position dims has to be equal to the sequence length.

Returns

An instance of ReformerConfig.

Return type

ReformerConfig

class transformers4rec.config.transformer.GPT2Config(vocab_size=50257, n_positions=1024, n_embd=768, n_layer=12, n_head=12, n_inner=None, activation_function='gelu_new', resid_pdrop=0.1, embd_pdrop=0.1, attn_pdrop=0.1, layer_norm_epsilon=1e-05, initializer_range=0.02, summary_type='cls_index', summary_use_proj=True, summary_activation=None, summary_proj_to_labels=True, summary_first_dropout=0.1, scale_attn_weights=True, use_cache=True, bos_token_id=50256, eos_token_id=50256, scale_attn_by_inverse_layer_idx=False, reorder_and_upcast_attn=False, **kwargs)

Bases: transformers4rec.config.transformer.T4RecConfig, transformers.models.gpt2.configuration_gpt2.GPT2Config

Subclass of T4RecConfig and transformers.GPT2Config from Hugging Face. It handles configuration for GPT2 layers in the context of T4Rec models.

classmethod build(d_model, n_head, n_layer, total_seq_length, hidden_act='gelu', initializer_range=0.01, layer_norm_eps=0.03, dropout=0.3, pad_token=0, log_attention_weights=False, **kwargs)

Creates an instance of GPT2Config with the given parameters.

Parameters

{transformer_cfg_parameters} –

Returns

An instance of GPT2Config.

Return type

GPT2Config

class transformers4rec.config.transformer.LongformerConfig(attention_window: Union[List[int], int] = 512, sep_token_id: int = 2, pad_token_id: int = 1, bos_token_id: int = 0, eos_token_id: int = 2, vocab_size: int = 30522, hidden_size: int = 768, num_hidden_layers: int = 12, num_attention_heads: int = 12, intermediate_size: int = 3072, hidden_act: str = 'gelu', hidden_dropout_prob: float = 0.1, attention_probs_dropout_prob: float = 0.1, max_position_embeddings: int = 512, type_vocab_size: int = 2, initializer_range: float = 0.02, layer_norm_eps: float = 1e-12, onnx_export: bool = False, **kwargs)

Bases: transformers4rec.config.transformer.T4RecConfig, transformers.models.longformer.configuration_longformer.LongformerConfig

Subclass of T4RecConfig and transformers.LongformerConfig from Hugging Face. It handles configuration for LongformerConfig layers in the context of T4Rec models.

classmethod build(d_model, n_head, n_layer, total_seq_length, hidden_act='gelu', initializer_range=0.01, layer_norm_eps=0.03, dropout=0.3, pad_token=0, log_attention_weights=False, **kwargs)

Creates an instance of LongformerConfig with the given parameters.

Parameters

{transformer_cfg_parameters} –

Returns

An instance of LongformerConfig.

Return type

LongformerConfig

class transformers4rec.config.transformer.ElectraConfig(vocab_size=30522, embedding_size=128, hidden_size=256, num_hidden_layers=12, num_attention_heads=4, intermediate_size=1024, hidden_act='gelu', hidden_dropout_prob=0.1, attention_probs_dropout_prob=0.1, max_position_embeddings=512, type_vocab_size=2, initializer_range=0.02, layer_norm_eps=1e-12, summary_type='first', summary_use_proj=True, summary_activation='gelu', summary_last_dropout=0.1, pad_token_id=0, position_embedding_type='absolute', use_cache=True, classifier_dropout=None, **kwargs)

Bases: transformers4rec.config.transformer.T4RecConfig, transformers.models.electra.configuration_electra.ElectraConfig

Subclass of T4RecConfig and transformers.ElectraConfig from Hugging Face. It handles configuration for ElectraConfig layers in the context of T4Rec models.

classmethod build(d_model, n_head, n_layer, total_seq_length, hidden_act='gelu', initializer_range=0.01, layer_norm_eps=0.03, dropout=0.3, pad_token=0, log_attention_weights=False, **kwargs)

Creates an instance of ElectraConfig with the given parameters.

Parameters

{transformer_cfg_parameters} –

Returns

An instance of ElectraConfig.

Return type

ElectraConfig

class transformers4rec.config.transformer.AlbertConfig(vocab_size=30000, embedding_size=128, hidden_size=4096, num_hidden_layers=12, num_hidden_groups=1, num_attention_heads=64, intermediate_size=16384, inner_group_num=1, hidden_act='gelu_new', hidden_dropout_prob=0, attention_probs_dropout_prob=0, max_position_embeddings=512, type_vocab_size=2, initializer_range=0.02, layer_norm_eps=1e-12, classifier_dropout_prob=0.1, position_embedding_type='absolute', pad_token_id=0, bos_token_id=2, eos_token_id=3, **kwargs)

Bases: transformers4rec.config.transformer.T4RecConfig, transformers.models.albert.configuration_albert.AlbertConfig

Subclass of T4RecConfig and transformers.AlbertConfig from Hugging Face. It handles configuration for AlbertConfig layers in the context of T4Rec models.

classmethod build(d_model, n_head, n_layer, total_seq_length, hidden_act='gelu', initializer_range=0.01, layer_norm_eps=0.03, dropout=0.3, pad_token=0, log_attention_weights=False, **kwargs)

Creates an instance of AlbertConfig with the given parameters.

Parameters

{transformer_cfg_parameters} –

Returns

An instance of AlbertConfig.

Return type

AlbertConfig

class transformers4rec.config.transformer.XLNetConfig(vocab_size=32000, d_model=1024, n_layer=24, n_head=16, d_inner=4096, ff_activation='gelu', untie_r=True, attn_type='bi', initializer_range=0.02, layer_norm_eps=1e-12, dropout=0.1, mem_len=512, reuse_len=None, use_mems_eval=True, use_mems_train=False, bi_data=False, clamp_len=- 1, same_length=False, summary_type='last', summary_use_proj=True, summary_activation='tanh', summary_last_dropout=0.1, start_n_top=5, end_n_top=5, pad_token_id=5, bos_token_id=1, eos_token_id=2, **kwargs)

Bases: transformers4rec.config.transformer.T4RecConfig, transformers.models.xlnet.configuration_xlnet.XLNetConfig

Subclass of T4RecConfig and transformers.XLNetConfig from Hugging Face. It handles configuration for XLNetConfig layers in the context of T4Rec models.

classmethod build(d_model, n_head, n_layer, total_seq_length=None, attn_type='bi', hidden_act='gelu', initializer_range=0.01, layer_norm_eps=0.03, dropout=0.3, pad_token=0, log_attention_weights=False, mem_len=1, **kwargs)

Creates an instance of XLNetConfig with the given parameters.

Parameters

• {transformer_cfg_parameters} –

• mem_len (int,) – The number of tokens to be cached. Pre-computed key/value pairs from a previous forward pass are stored and won’t be re-computed. This parameter is especially useful for long sequence modeling where different batches may truncate the entire sequence. Tasks like user-aware recommendation could benefit from this feature. By default, this parameter is set to 1, which means no caching is used.

Returns

An instance of XLNetConfig.

Return type

XLNetConfig

class transformers4rec.config.transformer.BertConfig(vocab_size=30522, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072, hidden_act='gelu', hidden_dropout_prob=0.1, attention_probs_dropout_prob=0.1, max_position_embeddings=512, type_vocab_size=2, initializer_range=0.02, layer_norm_eps=1e-12, pad_token_id=0, position_embedding_type='absolute', use_cache=True, classifier_dropout=None, **kwargs)

Bases: transformers4rec.config.transformer.T4RecConfig, transformers.models.bert.configuration_bert.BertConfig

Subclass of T4RecConfig and transformers.BertConfig from Hugging Face. It handles configuration for BertConfig layers in the context of T4Rec models.

classmethod build(d_model, n_head, n_layer, total_seq_length, hidden_act='gelu', initializer_range=0.01, layer_norm_eps=0.03, dropout=0.3, pad_token=0, log_attention_weights=False, **kwargs)

Creates an instance of BertConfig with the given parameters.

Parameters

{transformer_cfg_parameters} –

Returns

An instance of BertConfig.

Return type

BertConfig

class transformers4rec.config.transformer.RobertaConfig(vocab_size=50265, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072, hidden_act='gelu', hidden_dropout_prob=0.1, attention_probs_dropout_prob=0.1, max_position_embeddings=512, type_vocab_size=2, initializer_range=0.02, layer_norm_eps=1e-12, pad_token_id=1, bos_token_id=0, eos_token_id=2, position_embedding_type='absolute', use_cache=True, classifier_dropout=None, **kwargs)

Bases: transformers4rec.config.transformer.T4RecConfig, transformers.models.roberta.configuration_roberta.RobertaConfig

Subclass of T4RecConfig and transformers.RobertaConfig from Hugging Face. It handles configuration for RobertaConfig layers in the context of T4Rec models.

classmethod build(d_model, n_head, n_layer, total_seq_length, hidden_act='gelu', initializer_range=0.01, layer_norm_eps=0.03, dropout=0.3, pad_token=0, log_attention_weights=False, **kwargs)

Creates an instance of RobertaConfig with the given parameters.

Parameters

{transformer_cfg_parameters} –

Returns

An instance of RobertaConfig.

Return type

RobertaConfig

class transformers4rec.config.transformer.TransfoXLConfig(vocab_size=267735, cutoffs=[20000, 40000, 200000], d_model=1024, d_embed=1024, n_head=16, d_head=64, d_inner=4096, div_val=4, pre_lnorm=False, n_layer=18, mem_len=1600, clamp_len=1000, same_length=True, proj_share_all_but_first=True, attn_type=0, sample_softmax=- 1, adaptive=True, dropout=0.1, dropatt=0.0, untie_r=True, init='normal', init_range=0.01, proj_init_std=0.01, init_std=0.02, layer_norm_epsilon=1e-05, eos_token_id=0, **kwargs)

Bases: transformers4rec.config.transformer.T4RecConfig, transformers.models.transfo_xl.configuration_transfo_xl.TransfoXLConfig

Subclass of T4RecConfig and transformers. TransfoXLConfig from Hugging Face. It handles configuration for TransfoXLConfig layers in the context of T4Rec models.

classmethod build(d_model, n_head, n_layer, total_seq_length, hidden_act='gelu', initializer_range=0.01, layer_norm_eps=0.03, dropout=0.3, pad_token=0, log_attention_weights=False, **kwargs)

Creates an instance of TransfoXLConfig with the given parameters.

Parameters

{transformer_cfg_parameters} –

Returns

An instance of TransfoXLConfig.

Return type

TransfoXLConfig

Module contents