image-match/python/py/Lib/site-packages/transformers/models/musicflamingo/configuration_musicflamingo.py

#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/musicflamingo/modular_musicflamingo.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_musicflamingo.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2026 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/music-flamingo-2601-hf")
@strict
class MusicFlamingoConfig(PreTrainedConfig):
    r"""
    audio_bos_token_id (`int`, *optional*, defaults to 151670):
        The beginning-of-audio token index used to mark the start of audio spans.
    audio_eos_token_id (`int`, *optional*, defaults to 151671):
        The end-of-audio token index used to mark the end of audio spans.
    audio_frame_step (`float`, *optional*, defaults to 0.01):
        Duration in seconds of one input mel frame (trained with hop_length 160 at sampling_rate 16000).

    Example:

    ```python
    >>> from transformers import MusicFlamingoForConditionalGeneration, MusicFlamingoConfig, AudioFlamingo3EncoderConfig, Qwen2Config

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

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

    >>> # Initializing an MusicFlamingo configuration
    >>> configuration = MusicFlamingoConfig(audio_config, text_config)

    >>> # Initializing a model from the musicflamingo style configuration
    >>> model = MusicFlamingoForConditionalGeneration(configuration)

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

    model_type = "musicflamingo"
    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

    audio_bos_token_id: int = 151670
    audio_eos_token_id: int = 151671
    audio_frame_step: float = 0.01
    rope_parameters: dict | None = None

    def __post_init__(self, **kwargs):
        if isinstance(self.audio_config, dict):
            self.audio_config["model_type"] = self.audio_config.get("model_type", "musicflamingo_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["musicflamingo_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)

        if self.rope_parameters is None:
            self.rope_parameters = {"rope_type": "default", "rope_theta": 1200, "partial_rotary_factor": 0.2}
        self.max_position_embeddings = self.rope_parameters["rope_theta"]
        self.head_dim = self.audio_config.hidden_size


__all__ = ["MusicFlamingoConfig"]