from transformers.utils import logging
from transformers.configuration_utils import PretrainedConfig


logger = logging.get_logger(__name__)

INTERNLM_PRETRAINED_CONFIG_ARCHIVE_MAP = {}


class BufferEmbeddingConfig(PretrainedConfig):
    model_type = "buffer_embedding"
    _auto_class = "AutoConfig"
    keys_to_ignore_at_inference = ["past_key_values"]
    attribute_map = {
        "num_hidden_layers": "n_layer",
        "num_attention_heads": "n_head",
    }
    def __init__(
        self,
        vocab_size=250880,
        hidden_size=64,
        n_layer=2,
        n_head=8,
        layer_norm_epsilon=1e-5,
        initializer_range=0.02,
        use_cache=True,
        bos_token_id=1,
        eos_token_id=2,
        apply_residual_connection_post_layernorm=False,
        hidden_dropout=0.0,
        attention_dropout=0.0,
        pretraining_tp=1,  # TP rank used when training with megatron
        slow_but_exact=False,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        # Backward compatibility with n_embed kwarg
        n_embed = kwargs.pop("n_embed", None)
        self.hidden_size = hidden_size if n_embed is None else n_embed
        self.n_layer = n_layer
        self.n_head = n_head
        self.layer_norm_epsilon = layer_norm_epsilon
        self.initializer_range = initializer_range
        self.use_cache = use_cache
        self.pretraining_tp = pretraining_tp
        self.apply_residual_connection_post_layernorm = apply_residual_connection_post_layernorm
        self.hidden_dropout = hidden_dropout
        self.attention_dropout = attention_dropout

        self.bos_token_id = bos_token_id
        self.eos_token_id = eos_token_id
        self.slow_but_exact = slow_but_exact

        super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)