% &h,ddlmZGddeZdgZy))PretrainedConfigceZdZdZdZdgZddddddddZdgdgfd d gd gfd gd gfd Z d fd ZxZ S) HeliumConfiga This is the configuration class to store the configuration of a [`HeliumModel`]. It is used to instantiate an Helium 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 Helium 2b model. e.g. [kyutai/helium-2b](https://huggingface.co/kyutai/helium-2b) 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 48000): Vocabulary size of the Helium model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`HeliumModel`] hidden_size (`int`, *optional*, defaults to 2560): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 7040): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 24): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 20): Number of attention heads for each attention layer in the Transformer decoder. num_key_value_heads (`int`, *optional*, defaults to 20): 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`. 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 4096): 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-08): 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 100000.0): The base period of the RoPE embeddings. pad_token_id (`int`, *optional*, defaults to 3): Padding token id. eos_token_id (`int` | `list`, *optional*, defaults to 2): End of stream token id. bos_token_id (`int`, *optional*, defaults to 1): Beginning of stream token id. attention_bias (`bool`, *optional*, defaults to `False`): Whether to use a bias in the query, key, value and output projection layers during self-attention. 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. ```python >>> from transformers import HeliumModel, HeliumConfig >>> # Initializing a Helium 2b style configuration >>> configuration = HeliumConfig() >>> # Initializing a model from the Helium 2b style configuration >>> model = HeliumModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```heliumpast_key_valuescolwiserowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_proj input_ids inputs_embeds hidden_statesattention_mask) embed_tokenslayersnormc ||_| |_||_||_||_||_||_||_||_| |_ | |_ | |_ ||_ ||_ | |_||_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_headsnum_key_value_headshead_dim hidden_actinitializer_range rms_norm_eps use_cache rope_thetaattention_biasattention_dropoutmlp_biassuper__init__)selfrrrrrrrrr%rr r!r"rr#rrrr$r&kwargs __class__s /var/www/pru.catia.catastroantioquia-mas.com/valormas/lib/python3.12/site-packages/transformers/models/helium/configuration_helium.pyr(zHeliumConfig.__init__hs0%'>$&!2!2#6 #6   $!2("$,!2    %%% 3    )ii ir/silugig{Gz?g:0yE>TFgj@rFF) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr( __classcell__)r+s@r,rrs@ DJ#4"5%.%.%.%."+ )"+&(9:#%568IJ!"_$56 $!+/ / r-rN)configuration_utilsrr__all__rr-r,r?s$"4C #C L  r-