# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # This file was automatically generated from src/transformers/models/higgs_audio_v2/modular_higgs_audio_v2.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_higgs_audio_v2.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 ...configuration_utils import PreTrainedConfig class HiggsAudioV2Config(PreTrainedConfig): r""" This is the configuration class to store the configuration of a [`HiggsAudioV2Model`]. It is used to instantiate an HiggsAudioV2 model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the 3B model. e.g. [bosonai/higgs-audio-v2-generation-3B-base](https://huggingface.co/bosonai/higgs-audio-v2-generation-3B-base) Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 128256): Vocabulary size of the HiggsAudioV2 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`HiggsAudioV2Model`] hidden_size (`int`, *optional*, defaults to 3072): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 8192): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 28): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 24): Number of attention heads for each attention layer in the Transformer decoder. num_key_value_heads (`int`, *optional*, defaults to 8): This is the number of key_value heads that should be used to implement Grouped Query Attention. If `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if `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`. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the decoder. max_position_embeddings (`int`, *optional*, defaults to 2048): The maximum sequence length that this model might ever be used with. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. rms_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the rms normalization layers. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. pad_token_id (`int`, *optional*, defaults to 128001): Padding token id. bos_token_id (`int`, *optional*, defaults to 1): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 128009): End of stream token id. pretraining_tp (`int`, *optional*, defaults to 1): Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this document](https://huggingface.co/docs/transformers/main/perf_train_gpu_many#tensor-parallelism) to understand more about it. This value is necessary to ensure exact reproducibility of the pretraining results. Please refer to [this issue](https://github.com/pytorch/pytorch/issues/76232). tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings rope_parameters (`RopeParameters`, *optional*): Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE with longer `max_position_embeddings`. attention_bias (`bool`, *optional*, defaults to `False`): Whether to use a bias in the query, key, value and output projection layers during self-attention. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. mlp_bias (`bool`, *optional*, defaults to `False`): Whether to use a bias in up_proj, down_proj and gate_proj layers in the MLP layers. head_dim (`int`, *optional*, defaults to 128): The attention head dimension. If None, it will default to hidden_size // num_attention_heads num_codebooks (`int`, *optional*, defaults to 8): Number of codebooks used in the underlying codec model responsible for tokenizing the audio. codebook_size (`int`, *optional*, defaults to 1024): Size of the codebook used in the underlying codec model for audio tokenization. audio_token_id (`int`, *optional*, defaults to 128016): The token ID used to represent audio output in the text sequence. audio_bos_token_id (`int`, *optional*, defaults to 128013): The token ID for the beginning-of-sequence token for audio output. audio_delay_token_id (`int`, *optional*, defaults to 128014): The token ID used for audio delay pattern in multi-codebook generation. audio_stream_bos_id (`int`, *optional*, defaults to 1024): The ID for the beginning-of-stream token in audio sequences. audio_stream_eos_id (`int`, *optional*, defaults to 1025): The ID for the end-of-stream token in audio sequences. Example: ```python >>> from transformers import HiggsAudioV2Model, HiggsAudioV2Config >>> # Initializing a HiggsAudioV2 style configuration >>> configuration = HiggsAudioV2Config() >>> # Initializing a model from the configuration >>> model = HiggsAudioV2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "higgs_audio_v2" keys_to_ignore_at_inference = ["past_key_values"] # Default tensor parallel plan for base model `HiggsAudioV2Model` 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.gate_proj": "colwise", "layers.*.mlp.up_proj": "colwise", "layers.*.mlp.down_proj": "rowwise", } base_model_pp_plan = { "embed_tokens": (["input_ids"], ["inputs_embeds"]), "layers": (["hidden_states", "attention_mask"], ["hidden_states"]), "norm": (["hidden_states"], ["hidden_states"]), } def __init__( self, vocab_size=128256, hidden_size=3072, intermediate_size=8192, num_hidden_layers=28, num_attention_heads=24, num_key_value_heads=8, hidden_act="silu", max_position_embeddings=2048, initializer_range=0.02, rms_norm_eps=1e-05, use_cache=True, pad_token_id=128001, bos_token_id=1, eos_token_id=128009, pretraining_tp=1, tie_word_embeddings=False, rope_parameters={ "factor": 32.0, "rope_theta": 500000.0, "high_freq_factor": 0.5, "low_freq_factor": 0.125, "original_max_position_embeddings": 1024, "rope_type": "llama3", }, attention_bias=False, attention_dropout=0.0, mlp_bias=False, head_dim=128, num_codebooks=8, codebook_size=1024, audio_token_id=128016, audio_bos_token_id=128013, audio_delay_token_id=128014, audio_stream_bos_id=1024, audio_stream_eos_id=1025, **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.pretraining_tp = pretraining_tp self.use_cache = use_cache self.attention_bias = attention_bias self.attention_dropout = attention_dropout self.mlp_bias = mlp_bias self.head_dim = head_dim if head_dim is not None else self.hidden_size // self.num_attention_heads self.rope_parameters = rope_parameters self.tie_word_embeddings = tie_word_embeddings self.pad_token_id = pad_token_id self.bos_token_id = bos_token_id self.eos_token_id = eos_token_id super().__init__(**kwargs) self.num_codebooks = num_codebooks self.codebook_size = codebook_size self.audio_token_id = audio_token_id self.audio_bos_token_id = audio_bos_token_id self.audio_delay_token_id = audio_delay_token_id self.audio_stream_bos_id = audio_stream_bos_id self.audio_stream_eos_id = audio_stream_eos_id __all__ = ["HiggsAudioV2Config"]