o Zh@s@dZddlmZddlmZeeZGdddeZdgZ dS)z&Funnel Transformer model configuration)PretrainedConfig)loggingcseZdZdZdZdddZdgddd d d d d ddddddddddddffdd ZeddZej ddZeddZ e j ddZ Z S) FunnelConfiga This is the configuration class to store the configuration of a [`FunnelModel`] or a [`TFBertModel`]. It is used to instantiate a Funnel Transformer 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 Funnel Transformer [funnel-transformer/small](https://huggingface.co/funnel-transformer/small) 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 30522): Vocabulary size of the Funnel transformer. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`FunnelModel`] or [`TFFunnelModel`]. block_sizes (`List[int]`, *optional*, defaults to `[4, 4, 4]`): The sizes of the blocks used in the model. block_repeats (`List[int]`, *optional*): If passed along, each layer of each block is repeated the number of times indicated. num_decoder_layers (`int`, *optional*, defaults to 2): The number of layers in the decoder (when not using the base model). d_model (`int`, *optional*, defaults to 768): Dimensionality of the model's hidden states. n_head (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. d_head (`int`, *optional*, defaults to 64): Dimensionality of the model's heads. d_inner (`int`, *optional*, defaults to 3072): Inner dimension in the feed-forward blocks. hidden_act (`str` or `callable`, *optional*, defaults to `"gelu_new"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. hidden_dropout (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_dropout (`float`, *optional*, defaults to 0.1): The dropout probability for the attention probabilities. activation_dropout (`float`, *optional*, defaults to 0.0): The dropout probability used between the two layers of the feed-forward blocks. initializer_range (`float`, *optional*, defaults to 0.1): The upper bound of the *uniform initializer* for initializing all weight matrices in attention layers. initializer_std (`float`, *optional*): The standard deviation of the *normal initializer* for initializing the embedding matrix and the weight of linear layers. Will default to 1 for the embedding matrix and the value given by Xavier initialization for linear layers. layer_norm_eps (`float`, *optional*, defaults to 1e-09): The epsilon used by the layer normalization layers. pooling_type (`str`, *optional*, defaults to `"mean"`): Possible values are `"mean"` or `"max"`. The way pooling is performed at the beginning of each block. attention_type (`str`, *optional*, defaults to `"relative_shift"`): Possible values are `"relative_shift"` or `"factorized"`. The former is faster on CPU/GPU while the latter is faster on TPU. separate_cls (`bool`, *optional*, defaults to `True`): Whether or not to separate the cls token when applying pooling. truncate_seq (`bool`, *optional*, defaults to `True`): When using `separate_cls`, whether or not to truncate the last token when pooling, to avoid getting a sequence length that is not a multiple of 2. pool_q_only (`bool`, *optional*, defaults to `True`): Whether or not to apply the pooling only to the query or to query, key and values for the attention layers. Zfunneld_modeln_head)Z hidden_sizeZnum_attention_headsi:w)rrNi @i Zgelu_newg?gg& .>meanrelative_shiftTc s||_||_|durdgt|n||_t|t|jks!Jd||_||_||_||_||_| |_ | |_ | |_ | |_ | |_ ||_||_|dvsQJd|d||_|dvs`Jd|d||_||_||_||_tjdi|dS) Nz>`block_sizes` and `block_repeats` should have the same length.)r maxzGot z< for `pooling_type` but only 'mean' and 'max' are supported.)r Z factorizedzO for `attention_type` but only 'relative_shift' and 'factorized' are supported.) vocab_size block_sizeslen block_repeatsnum_decoder_layersrrd_headd_inner hidden_acthidden_dropoutattention_dropoutactivation_dropoutinitializer_rangeinitializer_stdlayer_norm_eps pooling_typeattention_type separate_cls truncate_seq pool_q_onlysuper__init__)selfrrrrrrrrrrrrrrrrrr r!r"kwargs __class__r^/var/www/auris/lib/python3.10/site-packages/transformers/models/funnel/configuration_funnel.pyr$Ys<    zFunnelConfig.__init__cC t|jSN)sumrr%rrr)num_hidden_layers zFunnelConfig.num_hidden_layerscCtd)NzYThis model does not support the setting of `num_hidden_layers`. Please set `block_sizes`.NotImplementedErrorr%valuerrr)r.scCr*r+)rrr-rrr) num_blocksr/zFunnelConfig.num_blockscCr0)NzRThis model does not support the setting of `num_blocks`. Please set `block_sizes`.r1r3rrr)r5s) __name__ __module__ __qualname____doc__Z model_typeZ attribute_mapr$propertyr.setterr5 __classcell__rrr'r)rsF::   rN) r9Zconfiguration_utilsrutilsrZ get_loggerr6loggerr__all__rrrr)s