T^(h (ldZddlmZddlmZddlmZejeZ GddeZ dgZ y)zPyTorch Phi-MoE model.)PretrainedConfig)rope_config_validation)loggingcdeZdZdZdZdgZ dfd 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 checkout [this paper](https://arxiv.org/pdf/2305.13245.pdf). 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_theta (`float`, *optional*, defaults to 1000000.0): The base period of the RoPE embeddings. rope_scaling (`dict`, *optional*): The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must contain the following keys: `type`, `short_factor`, `long_factor`, `short_mscale`, `long_mscale` and `original_max_position_embeddings`. The `type` must be `longrope`, the `short_mscale` and `long_scale` must be numbers, the `short_factor` and `long_factor` must be lists of numbers with the same length as half of the attention head size and the `original_max_position_embeddings` must be an integer. 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_valuesc t||_||_||_||_||_||_||_||_||_||}||_ ||_ | |_ | |_ | |_ ||_||_||_||_||_||_||_||_||_t/|j,t0rd|j,vr)|j,j3dd|j,d<d|j,vr|j,d|_|j,j3dd}|j,j3dd}t/|t6t8fst;d|t/|t6t8fst;d|t=|t?|d | | ||d|y) N rope_typetype original_max_position_embeddings short_mscale long_mscalez:`rope_scaling`'s short_mscale field must be a number, got z9`rope_scaling`'s long_mscale field must be a number, got ) pad_token_id bos_token_id eos_token_idtie_word_embeddings)! vocab_sizemax_position_embeddings hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headssliding_windowattention_bias lm_head_biasnum_key_value_heads hidden_actinitializer_range rms_norm_eps use_cache rope_thetaattention_dropoutnum_experts_per_toknum_local_expertsoutput_router_logitsrouter_aux_loss_coefrouter_jitter_noiseinput_jitter_noise rope_scaling isinstancedictgetr intfloat ValueErrorrsuper__init__) selfrrrrrrrrr r!r"rrrrr#r+rr$r%r&r'r(r)r*rrkwargsrope_scaling_short_mscalerope_scaling_long_mscale __class__s m/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/phimoe/configuration_phimoe.pyr3zPhimoeConfig.__init__ts>%'>$&!2!2#6 ,,(  &"5 #6 $!2("$!2#6 !2$8!$8!#6 "4( d'' .$"3"33151B1B1F1Fvt1T!!+.1T5F5FF8<8I8IJl8m5(,(9(9(=(=nd(S %'+'8'8'<'<]D'Q $7#uF PQjPkl6e E OPhOij t$  %%% 3    )i@}ii r;siluig{Gz?gh㈵>TNFg.ANNr?FgMbP?g{Gz?r@FF)__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencer3 __classcell__)r8s@r9rrsyT lJ#4"5 )!"" 9T T r:rN) rEconfiguration_utilsrmodeling_rope_utilsrutilsr get_loggerrBloggerr__all__rr:r9rOsA 39   H %n #n b  r: