o ߥµiµã@s$dZddlmZGdd„deƒZdS)z PLUG model configuration é)ÚPretrainedConfigcs>eZdZdZdZ       d‡fdd„ Z‡ZS)Ú PlugConfiga7 Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information. Args: vocab_size (:obj:`int`, `optional`, defaults to 30522): Vocabulary size of the BERT model. Defines the number of different tokens that can be represented by the :obj:`inputs_ids` passed when calling :class:`~transformers.BertModel` or :class:`~transformers.TFBertModel`. hidden_size (:obj:`int`, `optional`, defaults to 768): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (:obj:`int`, `optional`, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (:obj:`int`, `optional`, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (:obj:`int`, `optional`, defaults to 3072): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. hidden_act (:obj:`str` or :obj:`Callable`, `optional`, defaults to :obj:`"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, :obj:`"gelu"`, :obj:`"relu"`, :obj:`"silu"` and :obj:`"gelu_new"` are supported. hidden_dropout_prob (:obj:`float`, `optional`, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (:obj:`float`, `optional`, defaults to 0.1): The dropout ratio for the attention probabilities. max_position_embeddings (:obj:`int`, `optional`, defaults to 512): 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). type_vocab_size (:obj:`int`, `optional`, defaults to 2): The vocabulary size of the :obj:`token_type_ids` passed when calling :class:`~transformers.BertModel` or :class:`~transformers.TFBertModel`. initializer_range (:obj:`float`, `optional`, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layernorm_epsilon (:obj:`float`, `optional`, defaults to 1e-12): The epsilon used by the layer normalization layers. dec_hidden_layers (:obj:`int`, `optional`, defaults to 12): Number of hidden layers in the Transformer decoder. attn_separate (:obj:`bool`, `optional`, defaults to false): Whether or not to separate the q, k, v of attention. Examples:: >>> import PlugModel, PlugConfig >>> configuration = PlugConfig() >>> # Initializing a model from the configuration >>> model = PlugModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ÚplugÚrobertaú roberta-baseéFé ééé çš™™™™™É?Tçš™™™™™¹?c  s^tƒjdi| ¤Ž||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ dS)N©)ÚsuperÚ__init__ÚencoderÚ encoder_pthÚmax_posÚ share_embÚ dec_layersÚdec_hidden_sizeÚ dec_headsÚ dec_ff_sizeÚ dec_dropoutÚ use_bert_embÚlabel_smoothingÚ block_trigram)ÚselfrrrrrrrrrrrrÚkwargs©Ú __class__rú`/home/ubuntu/.local/lib/python3.10/site-packages/modelscope/models/nlp/fid_plug/configuration.pyrJs zPlugConfig.__init__) rrrFrr r r r Tr F)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typerÚ __classcell__rrrr!rs 3ôrN)r%Ú transformers.configuration_utilsrrrrrr!Ús