o ei/@sLdZddlmZddlmZddlmZeeZ GdddeZ dgZ dS)zPhi-3 model configuration)PreTrainedConfig)RopeParameters)loggingc,sveZdZdZdZdgZdddddZdgdgfd d gd gfd gd gfd Z                   d8dedBdedBdedBdedBdedBdedBd e dBd!e dBd"e dBd#e dBd$edBd%edBd&e dBd'edBd(e dBd)e dBd*e e e e fBdBd+edBd,edBd-edBd.edBf*fd/d0 Z d9d2ee Bd3edBfd4d5Zd:d3edBffd6d7 ZZS); 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, check out [this paper](https://huggingface.co/papers/2305.13245). 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_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`. 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_valuescolwise_gather_outputrowwise_split_input)zlayers.*.self_attn.qkv_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_up_projzlayers.*.mlp.down_proj input_ids inputs_embeds hidden_statesattention_mask) embed_tokenslayersnorm@} Nsilu{Gz?h㈵>TF} 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_cachetie_word_embeddingsrope_parameters bos_token_id eos_token_id pad_token_idsliding_windowc s||_||_||_||_||_|dur|}||_||_||_| |_| |_ | |_ | |_ | |_ ||_ ||_||_|dd||_||_||_||_||_tjdi|dS)Npartial_rotary_factorg?)rrrrr r!r"r#r$r%r&r'r(r)r*r, setdefaultr0r-r.r/r+super__init__)selfrrrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r0kwargs __class__r2i/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/phi3/configuration_phi3.pyr5ws2 zPhi3Config.__init__@ default_theta ignore_keyscKs|dd}|p |j|_|jdur|jni|_|jd|d||jd|d||jdd}|durC|dvrCd|jd<|j|d|S)N rope_scaling rope_thetar1 rope_type)suyarnlongroper=)popr,r3standardize_rope_paramsget validate_rope)r6r<r=r7r>rope_parameters_typer2r2r:convert_rope_params_to_dicts    z&Phi3Config.convert_rope_params_to_dictcsHtj|dt|jtstd|j|jdd}|jdd}|jdd}t|j|j |jd}|dvrBtd ||durqt|t rTt d d |Ds[td |t ||d ksqtd|d dt ||durt|t rt dd |Dstd|t ||d kstd|d dt |dSdS)z? Validate the `rope_parameters` configuration. rDz/`rope_parameters` must be a dictionary but got r@N short_factor long_factorr1)defaultrCz@`rope_parameters`'s type field must be one of ['longrope'], got cs|] }t|ttfVqdSN isinstanceintfloat.0xr2r2r: z+Phi3Config.validate_rope..zF`rope_parameters`'s short_factor field must be a list of numbers, got z8`rope_parameters`'s short_factor field must have length z, got csrNrOrPrTr2r2r:rWrXzE`rope_parameters`'s long_factor field must be a list of numbers, got z7`rope_parameters`'s long_factor field must have length ) r4rHrQr,dict ValueErrorrGrRrr listalllen)r6r=rIrope_parameters_short_factorrope_parameters_long_factor rotary_ndimsr8r2r:rHsJ zPhi3Config.validate_rope)rrrrrNrrrrrrrrTFNrrrN)r;NrO)__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planrRrSstrboolrrZr5setrJrH __classcell__r2r2r8r:rsO        7 rN) reconfiguration_utilsrmodeling_rope_utilsrutilsr get_loggerrbloggerr__all__r2r2r2r:s     U