qif#ldZddlmZddlmZddlmZejeZ GddeZ dgZ y)zGranite model configuration)PreTrainedConfig)RopeParameters)loggingc0eZdZdZdZdgZddddddddZdgdgfd d gd gfd gd gfd Z d%d ed zded zded zded zded zded zde d zded zde d zded zde d zded zded zded zde d zde e e e fzd zde d zde d zde d zd e d zd!e d zd"e d zd#e d zf.fd$ ZxZS)& GraniteConfiga This is the configuration class to store the configuration of a [`GraniteModel`]. It is used to instantiate an Granite 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 Granite-3B. 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 32000): Vocabulary size of the Granite model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`GraniteModel`] hidden_size (`int`, *optional*, defaults to 4096): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 11008): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 32): 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*): 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-06): 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*): Padding token id. bos_token_id (`int`, *optional*, defaults to 1): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 2): End of stream token id. 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. embedding_multiplier (`float`, *optional*, defaults to 1.0): embedding multiplier logits_scaling (`float`, *optional*, defaults to 1.0): divisor for output logits residual_multiplier (`float`, *optional*, defaults to 1.0): residual multiplier attention_multiplier (`float`, *optional*, defaults to 1.0): attention multiplier ```python >>> from transformers import GraniteModel, GraniteConfig >>> # Initializing a Granite granite-3b style configuration >>> configuration = GraniteConfig() >>> # Initializing a model from the granite-7b style configuration >>> model = GraniteModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```granitepast_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_tokenslayersnormN vocab_size hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsnum_key_value_heads hidden_actmax_position_embeddingsinitializer_range rms_norm_eps use_cache pad_token_id bos_token_id eos_token_idtie_word_embeddingsrope_parametersattention_biasattention_dropoutmlp_biasembedding_multiplierlogits_scalingresidual_multiplierattention_multiplierc n||_||_||_||_||_||_||}||_||_| |_| |_ | |_ ||_ ||_ ||_ ||_||_||_||_||_||_| |_| |_||_t/|`di|y)N)rrrrrrrrrrrr#r$r%r&r'r(r)r"r!rrr super__init__)selfrrrrrrrrrrrrrr r!r"r#r$r%r&r'r(r)kwargs __class__s c/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/granite/configuration_granite.pyr-zGraniteConfig.__init__|s6%'>$&!2!2#6   &"5 #6 $!2(",!2  $8!,#6 $8!.#6 ((( "6")i}ii+ r3Nsiluig{Gz?gư>TNFNFgF?r7r7r7)__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planintstrfloatboolrdictr- __classcell__)r0s@r1rrsJ XJ#4"5&/%.%.%."+ )"+&(9:#%568IJ!"_$56"'"&(-(**,*.!'.2*.#'!%#'#$#$+0MQ&+*- %-0'*,/-019#$J9#4Z9#: 9# : 9# !4Z 9#!4Z9#$J9#"%t9#!4<9#Dj9#$;9#Dj9#Dj9#Dj9# "D[!9#"($sN/B*CCdJ#9#$t %9#&!4<'9#(+)9#*$dl+9#, -9#.#T\/9#0$dl19#9#r2rN) r;configuration_utilsrmodeling_rope_utilsrutilsr get_loggerr8loggerr__all__r+r2r1rLsA&"31   H %X#$X#v  r2