fairseq/modules/sparse_transformer_sentence_encoder.py [19:43]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __init__(
        self,
        padding_idx: int,
        vocab_size: int,
        num_encoder_layers: int = 6,
        embedding_dim: int = 768,
        ffn_embedding_dim: int = 3072,
        num_attention_heads: int = 8,
        dropout: float = 0.1,
        attention_dropout: float = 0.1,
        activation_dropout: float = 0.1,
        max_seq_len: int = 256,
        num_segments: int = 2,
        use_position_embeddings: bool = True,
        offset_positions_by_padding: bool = True,
        encoder_normalize_before: bool = False,
        apply_bert_init: bool = False,
        activation_fn: str = "relu",
        learned_pos_embedding: bool = True,
        add_bias_kv: bool = False,
        add_zero_attn: bool = False,
        embed_scale: float = None,
        freeze_embeddings: bool = False,
        n_trans_layers_to_freeze: int = 0,
        export: bool = False,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



fairseq/modules/transformer_sentence_encoder.py [69:93]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def __init__(
        self,
        padding_idx: int,
        vocab_size: int,
        num_encoder_layers: int = 6,
        embedding_dim: int = 768,
        ffn_embedding_dim: int = 3072,
        num_attention_heads: int = 8,
        dropout: float = 0.1,
        attention_dropout: float = 0.1,
        activation_dropout: float = 0.1,
        max_seq_len: int = 256,
        num_segments: int = 2,
        use_position_embeddings: bool = True,
        offset_positions_by_padding: bool = True,
        encoder_normalize_before: bool = False,
        apply_bert_init: bool = False,
        activation_fn: str = "relu",
        learned_pos_embedding: bool = True,
        add_bias_kv: bool = False,
        add_zero_attn: bool = False,
        embed_scale: float = None,
        freeze_embeddings: bool = False,
        n_trans_layers_to_freeze: int = 0,
        export: bool = False,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -