T^(h`dZddlmZddlmZej eZGddeZdgZ y)zUDOP model configuration)PretrainedConfig)loggingcxeZdZdZdZdgZddddZdd d d d d dddddiddiddigddddddddd dddffd ZxZS) UdopConfiga This is the configuration class to store the configuration of a [`UdopForConditionalGeneration`]. It is used to instantiate a UDOP 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 UDOP [microsoft/udop-large](https://huggingface.co/microsoft/udop-large) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Arguments: vocab_size (`int`, *optional*, defaults to 33201): Vocabulary size of the UDOP model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`UdopForConditionalGeneration`]. d_model (`int`, *optional*, defaults to 1024): Size of the encoder layers and the pooler layer. d_kv (`int`, *optional*, defaults to 64): Size of the key, query, value projections per attention head. The `inner_dim` of the projection layer will be defined as `num_heads * d_kv`. d_ff (`int`, *optional*, defaults to 4096): Size of the intermediate feed forward layer in each `UdopBlock`. num_layers (`int`, *optional*, defaults to 24): Number of hidden layers in the Transformer encoder and decoder. num_decoder_layers (`int`, *optional*): Number of hidden layers in the Transformer decoder. Will use the same value as `num_layers` if not set. num_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder and decoder. relative_attention_num_buckets (`int`, *optional*, defaults to 32): The number of buckets to use for each attention layer. relative_attention_max_distance (`int`, *optional*, defaults to 128): The maximum distance of the longer sequences for the bucket separation. relative_bias_args (`List[dict]`, *optional*, defaults to `[{'type': '1d'}, {'type': 'horizontal'}, {'type': 'vertical'}]`): A list of dictionaries containing the arguments for the relative bias layers. dropout_rate (`float`, *optional*, defaults to 0.1): The ratio for all dropout layers. layer_norm_epsilon (`float`, *optional*, defaults to 1e-06): The epsilon used by the layer normalization layers. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). feed_forward_proj (`string`, *optional*, defaults to `"relu"`): Type of feed forward layer to be used. Should be one of `"relu"` or `"gated-gelu"`. Udopv1.1 uses the `"gated-gelu"` feed forward projection. Original Udop uses `"relu"`. is_encoder_decoder (`bool`, *optional*, defaults to `True`): Whether the model should behave as an encoder/decoder or not. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). pad_token_id (`int`, *optional*, defaults to 0): The id of the padding token in the vocabulary. eos_token_id (`int`, *optional*, defaults to 1): The id of the end-of-sequence token in the vocabulary. max_2d_position_embeddings (`int`, *optional*, defaults to 1024): The maximum absolute position embeddings for relative position encoding. image_size (`int`, *optional*, defaults to 224): The size of the input images. patch_size (`int`, *optional*, defaults to 16): The patch size used by the vision encoder. num_channels (`int`, *optional*, defaults to 3): The number of channels in the input images. udoppast_key_valuesd_model num_heads num_layers) hidden_sizenum_attention_headsnum_hidden_layersii@iN type1d horizontalverticalg?gư>g?reluTrc R||_||_||_||_||_||n |j|_||_||_| |_| |_ | |_ | |_ ||_ ||_ ||_||_||_||_t%| t&s t)d| |_|jj-d}|d|_|ddk(|_t3|dkDr|ddk7st3|dkDrt5d|d t7|pd |||d |y) Nz6`relative_bias_args` should be a list of dictionaries.-rgatedrz`feed_forward_proj`: z is not a valid activation function of the dense layer.Please make sure `feed_forward_proj` is of the format `gated-{ACT_FN}` or `{ACT_FN}`, e.g. 'gated-gelu' or 'relu') pad_token_id eos_token_idis_encoder_decoder) vocab_sizer d_kvd_ffr num_decoder_layersr relative_attention_num_bucketsrelative_attention_max_distance dropout_ratelayer_norm_epsiloninitializer_factorfeed_forward_proj use_cachemax_2d_position_embeddings image_size patch_size num_channels isinstancelist TypeErrorrelative_bias_argssplit dense_act_fn is_gated_actlen ValueErrorsuper__init__)selfr%r r&r'r r(r r)r*r7r+r,r-r.r#r/r!r"r0r1r2r3kwargsact_info __class__s i/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/udop/configuration_udop.pyr>zUdopConfig.__init__Ys[4%   $"4"@ doo #.L+/N,("4"4!2"+E'$$(,d3TU U"4))//4$RL$QK72 x=1 !!73x=1;L'(9':;))   %%1   ) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_mapr> __classcell__)rBs@rCrrs:xJ#4"5$-khtuM  ')(+#TNV\,BVZDXY #'/D D rDrN) rHconfiguration_utilsrutilsr get_loggerrEloggerr__all__r$rDrCrRs=3   H %E !E P .rD