sg,ddlmZGddeZdgZy))PretrainedConfigcZeZdZdZdZdgZdddddd d d d d dddddddgdddffd ZxZS) GlmConfiga This is the configuration class to store the configuration of a [`GlmModel`]. It is used to instantiate an Glm 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 Glm-4-9b-chat. e.g. [THUDM/glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat) 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 Glm model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`GlmModel`] hidden_size (`int`, *optional*, defaults to 4096): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 13696): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 40): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 32): Number of attention heads for each attention layer in the Transformer decoder. num_key_value_heads (`int`, *optional*, defaults to 2): 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 checkout [this paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `num_attention_heads`. partial_rotary_factor (`float`, *optional*, defaults to 0.5): The factor of the partial rotary position. head_dim (`int`, *optional*, defaults to 128): The attention head dimension. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The legacy activation function. It is overwritten by the `hidden_activation`. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. 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 1.5625e-07): 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 to tie weight embeddings rope_theta (`float`, *optional*, defaults to 10000.0): The base period of the RoPE embeddings. pad_token_id (`int`, *optional*, defaults to 151329): Padding token id. eos_token_id (`int` | `list`, *optional*, defaults to `[151329, 151336, 151338]`): End of stream token id. bos_token_id (`int`, *optional*): Beginning of stream token id. attention_bias (`bool`, defaults to `False`, *optional*, defaults to `True`): Whether to use a bias in the query, key, value and output projection layers during self-attention. ```python >>> from transformers import GlmModel, GlmConfig >>> # Initializing a Glm glm-4-9b-chat style configuration >>> configuration = GlmConfig() >>> # Initializing a model from the glm-4-9b-chat style configuration >>> model = GlmModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```glmpast_key_valuesiPii5( g?silugig{Gz?gh㈵>TFg@!O)r i(Oi*ONc ||_| |_||_||_||_||_||_||_||_| |_ | |_ | |_ ||_ ||_ ||_| |_t!|Dd||||d|y)N) pad_token_id bos_token_id eos_token_idtie_word_embeddings) vocab_sizemax_position_embeddings hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headspartial_rotary_factorhead_dimnum_key_value_heads hidden_actinitializer_range rms_norm_eps use_cache rope_thetaattention_biasattention_dropoutsuper__init__)selfrrrrrrrrrr#rrrr rr!rrrr"kwargs __class__s \/var/www/html/venv/lib/python3.12/site-packages/transformers/models/glm/configuration_glm.pyr%zGlmConfig.__init__Ys0%'>$&!2!2#6 %:"  #6 $!2("$,!2  %%% 3    )__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencer% __classcell__)r(s@r)rrsa? BJ#4"5! &"!-+/ / r*rN)configuration_utilsrr__all__rr*r)r4s#"4t  t n -r*