sgq)ZdZddlmZddlmZej eZGddeZy)zPhi-3 model configuration)PretrainedConfig)loggingcfeZdZdZdZdgZ dfd ZdZdZxZ S) Phi3Configa This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3 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-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-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 Phi-3 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Phi3Model`]. hidden_size (`int`, *optional*, defaults to 3072): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 8192): 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 checkout [this paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `num_attention_heads`. resid_pdrop (`float`, *optional*, defaults to 0.0): Dropout probability for mlp outputs. embd_pdrop (`int`, *optional*, defaults to 0.0): The dropout ratio for the embeddings. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio after computing the attention scores. 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): The maximum sequence length that this model might ever be used with. original_max_position_embeddings (`int`, *optional*, defaults to 4096): The maximum sequence length that this model was trained with. This is used to determine the size of the original RoPE embeddings when using long scaling. 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 value used for the RMSNorm. 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`. Whether to tie weight embeddings or not. 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. 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` and `long_factor`. The `type` must be `longrope` and the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size divided by the number of attention heads divided by 2. bos_token_id (`int`, *optional*, defaults to 1): The id of the "beginning-of-sequence" token. eos_token_id (`int`, *optional*, defaults to 32000): The id of the "end-of-sequence" token. pad_token_id (`int`, *optional*, defaults to 32000): The id of the padding token. sliding_window (`int`, *optional*): Sliding window attention window size. If `None`, no sliding window is applied. Example: ```python >>> from transformers import Phi3Model, Phi3Config >>> # Initializing a Phi-3 style configuration >>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct") >>> # Initializing a model from the configuration >>> model = Phi3Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```phi3past_key_valuesc r||_||_||_||_||_||}||_||_||_| |_| |_ | |_ | |_ | |_ ||_ ||_||_||_|j#|j%||_t)|Td||||d|y)N) bos_token_id eos_token_id pad_token_idtie_word_embeddings) vocab_size hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsnum_key_value_heads resid_pdrop embd_pdropattention_dropout hidden_actmax_position_embeddings original_max_position_embeddingsinitializer_range rms_norm_eps use_cache rope_theta rope_scaling_rope_scaling_adjustment_rope_scaling_validationsliding_windowsuper__init__)selfrrrrrrrrrrrrrrrr rrr r r r"kwargs __class__s ^/var/www/html/venv/lib/python3.12/site-packages/transformers/models/phi3/configuration_phi3.pyr$zPhi3Config.__init__os4%&!2!2#6  &"5 #6 &$!2$'>$0P-!2("$( %%' %%',  %%% 3    c|jy|jjdd}||dvrd|jd<yyy)zc Adjust the `type` of the `rope_scaling` configuration for backward compatibility. Ntype)suyarnlongrope)rget)r%rope_scaling_types r(r z#Phi3Config._rope_scaling_adjustmentsU    $  --11&$?  (->.-P(2D  f %.Q (r)c|jyt|jtrt|jdk7rt d|j|jj dd}|jj dd}|jj dd}||dvrt d|t|t rtd |Dst d |t||j|jzd zk(s4t d |j|jzd zd t|t|t rtd|Dst d|t||j|jzd zk(s4t d|j|jzd zd t|y)z< Validate the `rope_scaling` configuration. Nrze`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, got r+ short_factor long_factor)r.z=`rope_scaling`'s type field must be one of ['longrope'], got c3HK|]}t|ttfywN isinstanceintfloat.0xs r( z6Phi3Config._rope_scaling_validation..sSAJq3,/S "zC`rope_scaling`'s short_factor field must be a list of numbers, got z5`rope_scaling`'s short_factor field must have length z, got c3HK|]}t|ttfywr5r6r:s r(r=z6Phi3Config._rope_scaling_validation..sRAJq3,/Rr>zB`rope_scaling`'s long_factor field must be a list of numbers, got z4`rope_scaling`'s long_factor field must have length ) rr7dictlen ValueErrorr/listallrr)r%r0rope_scaling_short_factorrope_scaling_long_factors r(r!z#Phi3Config._rope_scaling_validations-    $ $++T2c$:K:K6LPQ6Q(()+ !--11&$?$($5$5$9$9.$$O!#'#4#4#8#8#M  $(9(M\]n\opq q 0$ 7S9RSSUVoUpq ,-1A1ATE]E]1]ab1bbGHXHX\`\t\tHtxyHyGz{ABEF_B`Aab  / 6R9QRRTUmTno +,0@0@DD\D\0\`a0aaFtGWGW[_[s[sGswxGxFyyADE]A^@_` br))i@}i i rHNrIrIsilurKg{Gz?gh㈵>TFg@N}rMN) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencer$r r! __classcell__)r's@r(rrsnP dJ#4"5  $)-!/9 v 3&r)rN) rQconfiguration_utilsrutilsr get_loggerrNloggerrrr)r(rYs3  3   H %D!Dr)