# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # This file was automatically generated from src/transformers/models/glm4_moe/modular_glm4_moe.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_glm4_moe.py file directly. One of our CI enforces this. # 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # Copyright 2025 The ZhipuAI Inc. team and 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 from ...modeling_rope_utils import RopeParameters class Glm4MoeConfig(PreTrainedConfig): r""" This is the configuration class to store the configuration of a [`Glm4MoeModel`]. It is used to instantiate a Glm4Moe model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of [THUDM/GLM-4-100B-A10B](https://huggingface.co/THUDM/GLM-4-100B-A10B). 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 151552): Vocabulary size of the Glm4Moe model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Glm4MoeModel`] hidden_size (`int`, *optional*, defaults to 4096): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 10944): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 46): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 96): Number of attention heads for each attention layer in the Transformer encoder. 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 `32`. 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 131072): 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`. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether the model's input and output word embeddings should be tied. 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`, defaults to `False`, *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. moe_intermediate_size (`int`, *optional*, defaults to 1408): Intermediate size of the routed expert. num_experts_per_tok (`int`, *optional*, defaults to 8): number of experts per token. n_shared_experts (`int`, *optional*, defaults to 1): Number of shared experts. n_routed_experts (`int`, *optional*, defaults to 128): Number of routed experts. routed_scaling_factor (`float`, *optional*, defaults to 1.0): Scaling factor or routed experts. n_group (`int`, *optional*, defaults to 1): Number of groups for routed experts. topk_group (`int`, *optional*, defaults to 1): Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups). first_k_dense_replace (`int`, *optional*, defaults to 1): Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head). \--k dense layers--/ norm_topk_prob (`bool`, *optional*, defaults to `True`): Whether to normalize the topk probabilities. use_qk_norm (`bool`, *optional*, defaults to `False`): Whether to use query-key normalization in the attention bos_token_id (`int`, *optional*): Beginning of stream token id. eos_token_id (`int`, *optional*): End of stream token id. pad_token_id (`int`, *optional*): Padding token id. ```python >>> from transformers import Glm4MoeModel, Glm4MoeConfig >>> # Initializing a Glm4Moe style configuration >>> configuration = Glm4MoeConfig() >>> # Initializing a model from the GLM-4-MOE-100B-A10B style configuration >>> model = Glm4MoeModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "glm4_moe" keys_to_ignore_at_inference = ["past_key_values"] # Default tensor parallel plan for base model `Glm4Moe` 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.experts.gate_up_proj": "rowwise", "layers.*.mlp.experts.down_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"]), } attribute_map = { "num_local_experts": "n_routed_experts", } def __init__( self, vocab_size: int | None = 151552, hidden_size: int | None = 4096, intermediate_size: int | None = 10944, num_hidden_layers: int | None = 46, num_attention_heads: int | None = 96, num_key_value_heads: int | None = 8, hidden_act: str | None = "silu", max_position_embeddings: int | None = 131072, initializer_range: float | None = 0.02, rms_norm_eps: int | None = 1e-5, use_cache: bool | None = True, tie_word_embeddings: bool | None = False, rope_parameters: RopeParameters | dict[str, RopeParameters] | None = None, attention_bias: bool | None = False, attention_dropout: float | None = 0.0, moe_intermediate_size: int | None = 1408, num_experts_per_tok: int | None = 8, n_shared_experts: int | None = 1, n_routed_experts: int | None = 128, routed_scaling_factor: float | None = 1.0, n_group: int | None = 1, topk_group: int | None = 1, first_k_dense_replace: int | None = 1, norm_topk_prob: bool | None = True, use_qk_norm: bool | None = False, bos_token_id: int | None = None, eos_token_id: int | None = None, pad_token_id: int | 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_bias = attention_bias self.attention_dropout = attention_dropout self.rope_parameters = rope_parameters kwargs.setdefault("partial_rotary_factor", 0.5) # assign default for BC # MoE arguments self.moe_intermediate_size = moe_intermediate_size self.num_experts_per_tok = num_experts_per_tok self.n_group = n_group self.topk_group = topk_group self.n_shared_experts = n_shared_experts self.n_routed_experts = n_routed_experts self.routed_scaling_factor = routed_scaling_factor self.first_k_dense_replace = first_k_dense_replace self.norm_topk_prob = norm_topk_prob self.use_qk_norm = use_qk_norm self.tie_word_embeddings = tie_word_embeddings self.bos_token_id = bos_token_id self.eos_token_id = eos_token_id self.pad_token_id = pad_token_id super().__init__(**kwargs) __all__ = ["Glm4MoeConfig"]