qia(ldZddlmZddlmZddlmZejeZ GddeZ dgZ y)zPyTorch Phi-MoE model.)PreTrainedConfig)RopeParameters)loggingc6eZdZdZdZdgZdZ d"dedzdedzdedzd edzd edzd edzd edzd edzde dzdedzde dzdedzdedzdedzdedzde e ee fzdzdedzde dzdedzdedzde dzde dzde dzde dzde dzde dzf4fd Z d#fd! ZxZS)$ PhimoeConfiga This is the configuration class to store the configuration of a [`PhimoeModel`]. It is used to instantiate a Phi-moe 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 [microsoft/Phi-3.5-MoE-instruct](https://huggingface.co/microsoft/Phi-3.5-MoE-instruct). 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 32064): Vocabulary size of the Phimoe model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`PhimoeModel`] hidden_size (`int`, *optional*, defaults to 4096): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 6400): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 32): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 32): 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 `8`. 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 `4096*32`): The maximum sequence length that this model might ever be used with. Mixtral's sliding window attention allows sequence of up to 4096*32 tokens. 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`. pad_token_id (`int`, *optional*): The id of the padding token. bos_token_id (`int`, *optional*, defaults to 1): The id of the "beginning-of-sequence" token. eos_token_id (`int`, *optional*, defaults to 2): 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. 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`. sliding_window (`int`, *optional*): Sliding window attention window size. If not specified, will default to `262144`. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. num_experts_per_tok (`int`, *optional*, defaults to 2): The number of experts to root per-token, can be also interpreted as the `top-p` routing parameter num_local_experts (`int`, *optional*, defaults to 16): Number of experts per Sparse MLP layer. output_router_logits (`bool`, *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 (`float`, *optional*, defaults to 0.001): The aux loss factor for the total loss. router_jitter_noise (`float`, *optional*, defaults to 0.01): Amount of noise to add to the router. input_jitter_noise (`float`, *optional*, defaults to 0.0): Input jitter noise attention_bias (`bool`, *optional*, defaults to `False`): Attention bias lm_head_bias (`bool`, *optional*, defaults to `False`): LM head bias Example: ```python >>> from transformers import PhimoeModel, PhimoeConfig >>> # Initializing a Phi-3 style configuration >>> configuration = PhimoeConfig.from_pretrained("microsoft/Phi-3.5-MoE-instruct") >>> # Initializing a model from the configuration >>> model = PhimoeModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```phimoepast_key_valuesg.AN 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_parameterssliding_windowattention_dropoutnum_experts_per_toknum_local_expertsoutput_router_logitsrouter_aux_loss_coefrouter_jitter_noiseinput_jitter_noiseattention_bias lm_head_biasc ||_||_||_||_||_||_||_||_||_||}||_ ||_ | |_ | |_ | |_ ||_||_||_||_||_||_||_||_||_| |_| |_||_t5|ldi|y)N)r rr r r rrr"r#rrrrrrrrrrr r!rrrrrsuper__init__)selfr r r r rrrrrrrrrrrrrrrrrrr r!r"r#kwargs __class__s a/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/phimoe/configuration_phimoe.pyr'zPhimoeConfig.__init__ps<%'>$&!2!2#6 ,,(  &"5 #6 $!2("!2#6 !2$8!$8!#6 "4.#6 ((( "6"ct|||jddk7rd|jvr|jd|_|jj dd}|jj dd}t |t tfstd|t |t tfstd |yy) z? Validate the `rope_parameters` configuration. ) ignore_keys rope_typedefault original_max_position_embeddings short_mscaleN long_mscalez=`rope_parameters`'s short_mscale field must be a number, got z<`rope_parameters`'s long_mscale field must be a number, got ) r& validate_roperr1get isinstanceintfloat TypeError)r(r.rope_parameters_short_mscalerope_parameters_long_mscaler*s r+r4zPhimoeConfig.validate_ropes +6    , 91T5I5II8<8L8LMo8p5+/+?+?+C+CNTX+Y (*.*>*>*B*B=RV*W ':S%LISTpSqr9C<HRSnRopI :r,)i@}ii r<siluig{Gz?gh㈵>TNFNNr@FgMbP?g{Gz?rAFF)N)__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference default_thetar7strr8boolrdictr'r4 __classcell__)r*s@r+rrsP dJ#4"5M"'"&(,(**,*+!'.7*.#'!%#'#$#$*/MQ%)*-*+(*,1-2,0+.&+$)7>#$J>#4Z>#: ># : ># !4Z >#!4Z>#$J>#"%t>#!4<>#Dj>#$;>#Dj>#Dj>#Dj># !4Z!>#"($sN/B*CCdJ#>#$d %>#&!4<'>#(!4Z)>#*:+>#,#Tk->#.$dl/>#0#T\1>#2"DL3>#4t 5>#6Tk7>#@r,rN) rFconfiguration_utilsrmodeling_rope_utilsrutilsr get_loggerrCloggerr__all__r%r,r+rTsA31   H %j#jZ  r,