#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright @2024 AI. Inspur Inc.
#
# @author: sunxian <sunxian@inspur.com>
# @date: 2024/07/18
#

from transformers.configuration_utils import PretrainedConfig


class HairuoConfig(PretrainedConfig):
    model_type = "hairuo"
    keys_to_ignore_at_inference = ["past_key_values"]
    _auto_class = "AutoConfig"

    def __init__(
        self,
        vocab_size=32000,
        hidden_size=4096,
        intermediate_size=14336,
        num_hidden_layers=32,
        num_attention_heads=32,
        num_key_value_heads=8,
        hidden_act="silu",
        max_position_embeddings=4096 * 32,
        initializer_range=0.02,
        rms_norm_eps=1e-6,
        use_cache=True,
        pad_token_id=None,
        bos_token_id=1,
        eos_token_id=2,
        tie_word_embeddings=False,
        rope_theta=8.4e5,
        rope_scaling=None,
        attention_dropout=0.0,
        mup_scale_emb=1,
        mup_scale_depth=32,
        mup_scale_width=1,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.max_position_embeddings = max_position_embeddings
        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads

        # for backward compatibility
        if num_key_value_heads is None:
            num_key_value_heads = num_attention_heads

        self.num_key_value_heads = num_key_value_heads
        self.hidden_act = hidden_act
        self.initializer_range = initializer_range
        self.rms_norm_eps = rms_norm_eps
        self.use_cache = use_cache
        self.rope_theta = rope_theta
        self.rope_scaling = rope_scaling
        self.attention_dropout = attention_dropout

        self.mup_scale_emb = mup_scale_emb
        self.mup_scale_depth = mup_scale_depth
        self.mup_scale_width = mup_scale_width

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