o ¾e¦iGã@s@dZddlmZddlmZe e¡ZGdd„deƒZdgZ dS)zCodeGen model configurationé)ÚPreTrainedConfig)ÚloggingcsXeZdZdZdZdddddœZ            d‡fdd„ Z‡ZS)Ú CodeGenConfiga² This is the configuration class to store the configuration of a [`CodeGenModel`]. It is used to instantiate a CodeGen 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 CodeGen [Salesforce/codegen-2B-mono](https://huggingface.co/Salesforce/codegen-2B-mono) architecture. 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 50400): Vocabulary size of the CodeGen model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`CodeGenModel`]. n_positions (`int`, *optional*, defaults to 2048): The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). n_ctx (`int`, *optional*, defaults to 2048): This attribute is used in `CodeGenModel.__init__` without any real effect. n_embd (`int`, *optional*, defaults to 4096): Dimensionality of the embeddings and hidden states. n_layer (`int`, *optional*, defaults to 28): Number of hidden layers in the Transformer encoder. n_head (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. rotary_dim (`int`, *optional*, defaults to 64): Number of dimensions in the embedding that Rotary Position Embedding is applied to. n_inner (`int`, *optional*): Dimensionality of the inner feed-forward layers. `None` will set it to 4 times n_embd activation_function (`str`, *optional*, defaults to `"gelu_new"`): Activation function, to be selected in the list `["relu", "silu", "gelu", "tanh", "gelu_new"]`. resid_pdrop (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. embd_pdrop (`int`, *optional*, defaults to 0.0): The dropout ratio for the embeddings. attn_pdrop (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention. layer_norm_epsilon (`float`, *optional*, defaults to 1e-05): The epsilon to use in the layer normalization layers. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). bos_token_id (`int`, *optional*, defaults to 50256): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 50256): End of stream token id. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether the model's input and output word embeddings should be tied. Note that this is only relevant if the model has a output word embedding layer. Example: ```python >>> from transformers import CodeGenConfig, CodeGenModel >>> # Initializing a CodeGen 6B configuration >>> configuration = CodeGenConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = CodeGenModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ÚcodegenÚ n_positionsÚn_embdÚn_headÚn_layer)Úmax_position_embeddingsÚ hidden_sizeÚnum_attention_headsÚnum_hidden_layerséàÄééééé@NÚgelu_newççñh㈵øä>ç{®Gáz”?TéPÄFc sŽ||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ | |_ ||_ ||_||_||_||_||_||_tƒjdi|¤ŽdS)N©)Ú vocab_sizeÚn_ctxrrr rÚn_innerÚ rotary_dimÚactivation_functionÚ resid_pdropÚ embd_pdropÚ attn_pdropÚlayer_norm_epsilonÚinitializer_rangeÚ use_cacheÚ bos_token_idÚ eos_token_idÚtie_word_embeddingsÚsuperÚ__init__)Úselfrrrrr rrrrrr r!r"r#r$r%r&r'Úkwargs©Ú __class__rúo/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/codegen/configuration_codegen.pyr)`s*zCodeGenConfig.__init__)rrrrrrrNrrrrrrTrrF)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚ attribute_mapr)Ú __classcell__rrr,r.rs6@ü írN) r2Úconfiguration_utilsrÚutilsrÚ get_loggerr/ÚloggerrÚ__all__rrrr.Ús     x