# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # This file was automatically generated from src/transformers/models/minimax_m2/modular_minimax_m2.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_minimax_m2.py file directly. One of our CI enforces this. # 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # Copyright 2025 the MiniMax AI Team and HuggingFace 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 from ...modeling_rope_utils import RopeParameters class MiniMaxM2Config(PreTrainedConfig): r""" This is the configuration class to store the configuration of a [`MiniMaxM2Model`]. It is used to instantiate an MiniMaxM2 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 MiniMaxM2. [MiniMaxAI/MiniMax-M2](https://huggingface.co/MiniMaxAI/MiniMax-M2) 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 (`Optional`, *optional*, defaults to 200064): Vocabulary size of the MiniMaxM2 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`MiniMaxM2Model`] hidden_size (`Optional`, *optional*, defaults to 3072): Dimension of the hidden representations. intermediate_size (`Optional`, *optional*, defaults to 1536): Dimension of the MLP representations. num_hidden_layers (`Optional`, *optional*, defaults to 62): Number of hidden layers in the Transformer encoder. num_attention_heads (`Optional`, *optional*, defaults to 48): Number of attention heads for each attention layer in the Transformer encoder. num_key_value_heads (`Optional`, *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 `8`. head_dim (`Optional`, *optional*, defaults to 128): The attention head dimension. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the decoder. max_position_embeddings (`Optional`, *optional*, defaults to 196608): The maximum sequence length that this model might ever be used with. MiniMaxM2's sliding window attention allows sequence of up to 196608 tokens. initializer_range (`Optional`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. rms_norm_eps (`Optional`, *optional*, defaults to 1e-06): The epsilon used by the rms normalization layers. use_cache (`Optional`, *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 (`Optional`, *optional*): The id of the padding token. bos_token_id (`Optional`, *optional*, defaults to 200034): The id of the "beginning-of-sequence" token. eos_token_id (`Optional`, *optional*, defaults to 200020): The id of the "end-of-sequence" token. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether the model's input and output word embeddings should be tied. attention_dropout (`Optional`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. num_experts_per_tok (`Optional`, *optional*, defaults to 8): The number of experts to route per-token, can be also interpreted as the `top-k` routing parameter num_local_experts (`Optional`, *optional*, defaults to 256): Number of experts per Sparse MLP layer. output_router_logits (`Optional`, *optional*, defaults to `False`): Whether or not the router logits should be returned by the model. Enabling this will also allow the model to output the auxiliary loss. See [here]() for more details router_aux_loss_coef (`Optional`, *optional*, defaults to 0.001): The aux loss factor for the total loss. router_jitter_noise (`Optional`, *optional*, defaults to 0.0): Amount of noise to add to the router. rope_parameters (`RopeParameters`, *optional*): Dictionary containing the configuration parameters for the RoPE embeddings. The dictionaty 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`. ```python >>> from transformers import MiniMaxM2Model, MiniMaxM2Config >>> # Initializing a MiniMaxM2 style configuration >>> configuration = MiniMaxM2Config() >>> # Initializing a model from the MiniMaxM2 style configuration >>> model = MiniMaxM2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "minimax_m2" keys_to_ignore_at_inference = ["past_key_values"] base_model_tp_plan = { "layers.*.self_attn.q_proj": "colwise_rep", "layers.*.self_attn.k_proj": "colwise_rep", "layers.*.self_attn.v_proj": "colwise_rep", "layers.*.self_attn.o_proj": "rowwise_rep", "layers.*.mlp.gate": "colwise_rep", # we need to replicate here to correctly route experts "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", } default_theta = 5000000.0 def __init__( self, vocab_size: int | None = 200064, hidden_size: int | None = 3072, intermediate_size: int | None = 1536, num_hidden_layers: int | None = 62, num_attention_heads: int | None = 48, num_key_value_heads: int | None = 8, head_dim: int | None = 128, hidden_act: str | None = "silu", max_position_embeddings: int | None = 196608, initializer_range: float | None = 0.02, rms_norm_eps: int | None = 1e-06, use_cache: bool | None = True, pad_token_id: int | None = None, bos_token_id: int | None = 200034, eos_token_id: int | None = 200020, tie_word_embeddings: bool | None = False, attention_dropout: float | None = 0.0, num_experts_per_tok: int | None = 8, num_local_experts: int | None = 256, output_router_logits: bool | None = False, router_aux_loss_coef: float | None = 0.001, router_jitter_noise: float | None = 0.0, rope_parameters: RopeParameters | dict[RopeParameters] | None = None, **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 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.use_cache = use_cache self.attention_dropout = attention_dropout self.head_dim = head_dim self.rope_parameters = rope_parameters self.num_experts_per_tok = num_experts_per_tok self.num_local_experts = num_local_experts self.output_router_logits = output_router_logits self.router_aux_loss_coef = router_aux_loss_coef self.router_jitter_noise = router_jitter_noise self.pad_token_id = pad_token_id self.bos_token_id = bos_token_id self.eos_token_id = eos_token_id self.tie_word_embeddings = tie_word_embeddings super().__init__(**kwargs) __all__ = ["MiniMaxM2Config"]