# Copyright 2025 NVIDIA CORPORATION 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.


from huggingface_hub.dataclasses import strict

from ...configuration_utils import PreTrainedConfig
from ...utils import auto_docstring
from ..auto import CONFIG_MAPPING, AutoConfig


@auto_docstring(checkpoint="nvidia/audio-flamingo-3-hf")
@strict
class AudioFlamingo3EncoderConfig(PreTrainedConfig):
    r"""
    max_source_positions (`int`, *optional*, defaults to 1500):
        The maximum sequence length of log-mel filter-bank features that this model might ever be used with.

    Example:

    ```python
    >>> from transformers import AudioFlamingo3EncoderConfig, AudioFlamingo3Encoder

    >>> # Initializing an AudioFlamingo3EncoderConfig
    >>> configuration = AudioFlamingo3EncoderConfig()

    >>> # Initializing an AudioFlamingo3Encoder (with random weights)
    >>> model = AudioFlamingo3Encoder(configuration)

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

    model_type = "audioflamingo3_encoder"

    attribute_map = {
        "d_model": "hidden_size",
        "encoder_layers": "num_hidden_layers",
        "encoder_attention_heads": "num_attention_heads",
        "encoder_ffn_dim": "intermediate_size",
        "encoder_layerdrop": "layerdrop",
    }

    num_mel_bins: int = 128
    num_hidden_layers: int = 32
    num_attention_heads: int = 20
    intermediate_size: int = 5120
    layerdrop: float | int = 0.0
    activation_function: str = "gelu"
    hidden_size: int = 1280
    dropout: float | int = 0.0
    attention_dropout: float | int = 0.0
    activation_dropout: float | int = 0.0
    initializer_range: float = 0.02
    scale_embedding: bool = False
    max_source_positions: int = 1500


@auto_docstring(checkpoint="nvidia/audio-flamingo-3-hf")
@strict
class AudioFlamingo3Config(PreTrainedConfig):
    r"""
    Example:

    ```python
    >>> from transformers import AudioFlamingo3ForConditionalGeneration, AudioFlamingo3Config, AudioFlamingo3EncoderConfig, Qwen2Config

    >>> # Initializing an AudioFlamingo3Encoder config
    >>> audio_config = AudioFlamingo3EncoderConfig()

    >>> # Initializing a Qwen2 config
    >>> text_config = Qwen2Config()

    >>> # Initializing an AudioFlamingo3 configuration
    >>> configuration = AudioFlamingo3Config(audio_config, text_config)

    >>> # Initializing a model from the audioflamingo3 style configuration
    >>> model = AudioFlamingo3ForConditionalGeneration(configuration)

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

    model_type = "audioflamingo3"
    sub_configs = {"audio_config": AutoConfig, "text_config": AutoConfig}
    audio_config: dict | PreTrainedConfig | None = None
    text_config: dict | PreTrainedConfig | None = None
    audio_token_id: int = 151669
    projector_hidden_act: str = "gelu"
    projector_bias: bool = True

    def __post_init__(self, **kwargs):
        if isinstance(self.audio_config, dict):
            self.audio_config["model_type"] = self.audio_config.get("model_type", "audioflamingo3_encoder")
            self.audio_config = CONFIG_MAPPING[self.audio_config["model_type"]](**self.audio_config)
        elif self.audio_config is None:
            self.audio_config = CONFIG_MAPPING["audioflamingo3_encoder"]()

        if isinstance(self.text_config, dict):
            self.text_config["model_type"] = self.text_config.get("model_type", "qwen2")
            self.text_config = CONFIG_MAPPING[self.text_config["model_type"]](**self.text_config)
        elif self.text_config is None:
            self.text_config = CONFIG_MAPPING["qwen2"]()

        super().__post_init__(**kwargs)


__all__ = ["AudioFlamingo3Config", "AudioFlamingo3EncoderConfig"]