from __future__ import annotations

import json
import pathlib
import copy
from transformers.configuration_utils import PretrainedConfig

class MTPGPT2Config(PretrainedConfig):
    model_type = "mtp_gpt2"
    keys_to_ignore_at_inference = ["past_key_values"]
    attribute_map = {
        "hidden_size": "n_embd",
        "max_position_embeddings": "n_positions",
        "num_attention_heads": "n_head",
        "num_hidden_layers": "n_layer",
    }

    def __init__(
        self,
        vocab_size=16384,
        n_positions=512,
        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-5,
        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=1,
        eos_token_id=2,
        pad_token_id=3,
        scale_attn_by_inverse_layer_idx=False,
        reorder_and_upcast_attn=False,
        n_future_tokens=2, 
        curriculum=True, 
        curriculum_type="backward",
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.n_positions = n_positions
        self.n_embd = n_embd
        self.n_layer = n_layer
        self.n_head = n_head
        self.n_inner = n_inner
        self.activation_function = activation_function
        self.resid_pdrop = resid_pdrop
        self.embd_pdrop = embd_pdrop
        self.attn_pdrop = attn_pdrop
        self.layer_norm_epsilon = layer_norm_epsilon
        self.initializer_range = initializer_range
        self.summary_type = summary_type
        self.summary_use_proj = summary_use_proj
        self.summary_activation = summary_activation
        self.summary_first_dropout = summary_first_dropout
        self.summary_proj_to_labels = summary_proj_to_labels
        self.scale_attn_weights = scale_attn_weights
        self.use_cache = use_cache
        self.scale_attn_by_inverse_layer_idx = scale_attn_by_inverse_layer_idx
        self.reorder_and_upcast_attn = reorder_and_upcast_attn
        self.n_future_tokens = n_future_tokens
        self.curriculum = curriculum
        self.curriculum_type = curriculum_type

        self.bos_token_id = bos_token_id
        self.eos_token_id = eos_token_id
        self.pad_token_id = pad_token_id

        super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, pad_token_id=pad_token_id, **kwargs)
    
    def to_dict(self) -> dict:
        """Serializes this instance to a Python dictionary."""
        output: dict

        output = copy.deepcopy(self.__dict__)
        return output

    def to_json_string(self) -> str:
        """Serializes this instance to a JSON string."""
        return json.dumps(self.to_dict(), indent=2, sort_keys=True, default=str) + "\n"

    def to_json_file(self, json_file_path: pathlib.Path | str, **kwargs) -> None:
        """Save this instance to a json file."""
        if isinstance(json_file_path, str):
            json_file_path: pathlib.Path = pathlib.Path(json_file_path)
        with json_file_path.open("w", encoding='utf-8') as writer:
            writer.write(self.to_json_string())