o ¾e¦ip ã@sLdZddlmZddlmZddlmZe e¡Z Gdd„deƒZ dgZ dS)zPhi model configurationé)ÚPreTrainedConfig)ÚRopeParameters)Úloggingc*sDeZdZdZdZdgZdddddddœZdgdgfdgdgfd d gd gfd gd gfd œZ                 d0dedBdedBdedBdedBdedBdedBd e dBd!e dBd"e dBd#e dBd$edBd%e dBd&edBd'e dBd(e dBd)e e e e fBdBd*e dBd+edBd,edBd-edBf(‡fd.d/„ Z‡ZS)1Ú PhiConfiga This is the configuration class to store the configuration of a [`PhiModel`]. It is used to instantiate an Phi 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 Phi [microsoft/phi-1](https://huggingface.co/microsoft/phi-1). 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 51200): Vocabulary size of the Phi model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`PhiModel`]. hidden_size (`int`, *optional*, defaults to 2048): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 8192): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 24): 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 `"gelu_new"`): 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. Phi-1 and Phi-1.5 supports up to 2048 tokens. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_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`. 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`. qk_layernorm (`bool`, *optional*, defaults to `False`): Whether or not to normalize the Queries and Keys after projecting the hidden states. bos_token_id (`int`, *optional*, defaults to 1): Denotes beginning of sequences token id. eos_token_id (`int`, *optional*, defaults to 2): Denotes end of sequences token id. pad_token_id (`int`, *optional*): The id of the padding token. Example: ```python >>> from transformers import PhiModel, PhiConfig >>> # Initializing a Phi-1 style configuration >>> configuration = PhiConfig.from_pretrained("microsoft/phi-1") >>> # Initializing a model from the configuration >>> model = PhiModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ÚphiÚpast_key_valuesÚcolwiseÚrowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.densezlayers.*.mlp.fc1zlayers.*.mlp.fc2Ú input_idsÚ inputs_embedsÚ hidden_statesÚattention_mask)Ú embed_tokensÚ embed_dropoutÚlayersÚfinal_layernorméÈéé éé NçÚgelu_newç{®Gáz”?çñh㈵øä>TFééÚ vocab_sizeÚ hidden_sizeÚintermediate_sizeÚnum_hidden_layersÚnum_attention_headsÚnum_key_value_headsÚ resid_pdropÚ embd_pdropÚattention_dropoutÚ hidden_actÚmax_position_embeddingsÚinitializer_rangeÚlayer_norm_epsÚ use_cacheÚtie_word_embeddingsÚrope_parametersÚ qk_layernormÚ bos_token_idÚ eos_token_idÚ pad_token_idc s¦||_||_||_||_||_|dur|}||_||_||_| |_| |_ | |_ | |_ | |_ ||_ ||_||_| dd¡||_||_||_||_tƒjdi|¤ŽdS)NÚpartial_rotary_factorgà?©)rrrr r!r"r#r$r%r&r'r(r)r*r-r,Ú setdefaultr.r/r0r+ÚsuperÚ__init__)Úselfrrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r0Úkwargs©Ú __class__r2úg/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/phi/configuration_phi.pyr5xs0 zPhiConfig.__init__)rrrrrNrrrrrrrTFNFrrN)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planÚintÚfloatÚstrÚboolrÚdictr5Ú __classcell__r2r2r8r:rsšMú   ü ëþýüûúùø ÷ ö õ ô óòñðïîíìërN) r>Úconfiguration_utilsrÚmodeling_rope_utilsrÚutilsrÚ get_loggerr;ÚloggerrÚ__all__r2r2r2r:Ús