#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/moonshine/modular_moonshine.py.
#               Do NOT edit this file manually as any edits will be overwritten by the generation of
#             the file from the modular. If any change should be done, please apply the change to the
#                          modular_moonshine.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2025 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.

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="UsefulSensors/moonshine-tiny")
@strict
class MoonshineConfig(PreTrainedConfig):
    r"""
    encoder_num_key_value_heads (`int`, *optional*):
        This is the number of key_value heads that should be used to implement Grouped Query Attention. If
        `encoder_num_key_value_heads=encoder_num_attention_heads`, the model will use Multi Head Attention (MHA), if
        `encoder_num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
        converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
        by meanpooling all the original heads within that group. For more details, check out [this
        paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to
        `num_attention_heads`.
    decoder_num_key_value_heads (`int`, *optional*):
        This is the number of key_value heads that should be used to implement Grouped Query Attention. If
        `decoder_num_key_value_heads=decoder_num_attention_heads`, the model will use Multi Head Attention (MHA), if
        `decoder_num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
        converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
        by meanpooling all the original heads within that group. For more details, check out [this
        paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to
        `decoder_num_attention_heads`.
    pad_head_dim_to_multiple_of (`int`, *optional*):
        Pad head dimension in encoder and decoder to the next multiple of this value. Necessary for using certain
        optimized attention implementations.
    encoder_hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
        The non-linear activation function (function or string) in the encoder.
    decoder_hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
        The non-linear activation function (function or string) in the decoder.

    Example:

    ```python
    >>> from transformers import MoonshineModel, MoonshineConfig

    >>> # Initializing a Moonshine style configuration
    >>> configuration = MoonshineConfig().from_pretrained("UsefulSensors/moonshine-tiny")

    >>> # Initializing a model from the configuration
    >>> model = MoonshineModel(configuration)

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

    model_type = "moonshine"
    keys_to_ignore_at_inference = ["past_key_values"]
    attribute_map = {
        "num_key_value_heads": "decoder_num_key_value_heads",
        "num_attention_heads": "decoder_num_attention_heads",
        "num_hidden_layers": "decoder_num_hidden_layers",
        "hidden_act": "decoder_hidden_act",
    }

    vocab_size: int = 32768
    hidden_size: int = 288
    intermediate_size: int = 1152
    encoder_num_hidden_layers: int = 6
    decoder_num_hidden_layers: int = 6
    encoder_num_attention_heads: int = 8
    decoder_num_attention_heads: int = 8
    encoder_num_key_value_heads: int | None = None
    decoder_num_key_value_heads: int | None = None
    pad_head_dim_to_multiple_of: int | None = None
    encoder_hidden_act: str = "gelu"
    decoder_hidden_act: str = "silu"
    max_position_embeddings: int = 512
    initializer_range: float = 0.02
    decoder_start_token_id: int = 1
    use_cache: bool = True
    rope_parameters: RopeParameters | dict | None = None
    is_encoder_decoder: bool = True
    attention_bias: bool = False
    attention_dropout: float | int = 0.0
    bos_token_id: int | None = 1
    eos_token_id: int | list[int] | None = 2
    pad_token_id: int | None = None
    tie_word_embeddings: bool = True

    def __post_init__(self, **kwargs):
        if self.encoder_num_key_value_heads is None:
            self.encoder_num_key_value_heads = self.encoder_num_attention_heads

        if self.decoder_num_key_value_heads is None:
            self.decoder_num_key_value_heads = self.decoder_num_attention_heads

        kwargs.setdefault("partial_rotary_factor", 0.9)  # assign default for BC
        super().__post_init__(**kwargs)


__all__ = ["MoonshineConfig"]