# Copyright 2023 Mixtral AI and the HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Mixtral model configuration"""

from huggingface_hub.dataclasses import strict

from ...configuration_utils import PreTrainedConfig
from ...modeling_rope_utils import RopeParameters
from ...utils import auto_docstring


@auto_docstring(checkpoint="mistralai/Mixtral-8x7B-v0.1")
@strict
class MixtralConfig(PreTrainedConfig):
    r"""
    Example:

    ```python
    >>> from transformers import MixtralModel, MixtralConfig

    >>> # Initializing a Mixtral 7B style configuration
    >>> configuration = MixtralConfig()

    >>> # Initializing a model from the Mixtral 7B style configuration
    >>> model = MixtralModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "mixtral"
    keys_to_ignore_at_inference = ["past_key_values"]
    default_theta = 1000000.0
    base_model_tp_plan = {
        "layers.*.self_attn.q_proj": "colwise",
        "layers.*.self_attn.k_proj": "colwise",
        "layers.*.self_attn.v_proj": "colwise",
        "layers.*.self_attn.o_proj": "rowwise",
        "layers.*.mlp.experts.gate_up_proj": "packed_colwise",
        "layers.*.mlp.experts.down_proj": "rowwise",
        "layers.*.mlp.experts": "moe_tp_experts",
    }
    base_model_pp_plan = {
        "embed_tokens": (["input_ids"], ["inputs_embeds"]),
        "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
        "norm": (["hidden_states"], ["hidden_states"]),
    }
    attribute_map = {"num_experts": "num_local_experts"}

    vocab_size: int = 32000
    hidden_size: int = 4096
    intermediate_size: int = 14336
    num_hidden_layers: int = 32
    num_attention_heads: int = 32
    num_key_value_heads: int = 8
    head_dim: int | None = None
    hidden_act: str = "silu"
    max_position_embeddings: int = 4096 * 32
    initializer_range: float = 0.02
    rms_norm_eps: float = 1e-5
    use_cache: bool = True
    pad_token_id: int | None = None
    bos_token_id: int | None = 1
    eos_token_id: int | list[int] | None = 2
    tie_word_embeddings: bool = False
    sliding_window: int | None = None
    attention_dropout: float | int = 0.0
    num_experts_per_tok: int = 2
    num_local_experts: int = 8
    output_router_logits: bool = False
    router_aux_loss_coef: float = 0.001
    router_jitter_noise: float = 0.0
    rope_parameters: RopeParameters | dict | None = None

    def __post_init__(self, **kwargs):
        if self.num_key_value_heads is None:
            self.num_key_value_heads = self.num_attention_heads

        super().__post_init__(**kwargs)


__all__ = ["MixtralConfig"]