qi`dZddlmZddlmZej eZGddeZdgZ y)zBlenderbot model configuration)PreTrainedConfig)loggingcneZdZdZdZdgZdddZ dfd ZxZS) BlenderbotConfiga This is the configuration class to store the configuration of a [`BlenderbotModel`]. It is used to instantiate an Blenderbot 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 Blenderbot [facebook/blenderbot-3B](https://huggingface.co/facebook/blenderbot-3B) 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 50265): Vocabulary size of the Blenderbot model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`BlenderbotModel`]. d_model (`int`, *optional*, defaults to 1024): Dimensionality of the layers and the pooler layer. encoder_layers (`int`, *optional*, defaults to 12): Number of encoder layers. decoder_layers (`int`, *optional*, defaults to 12): Number of decoder layers. encoder_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. decoder_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer decoder. decoder_ffn_dim (`int`, *optional*, defaults to 4096): Dimensionality of the "intermediate" (often named feed-forward) layer in decoder. encoder_ffn_dim (`int`, *optional*, defaults to 4096): Dimensionality of the "intermediate" (often named feed-forward) layer in decoder. activation_function (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. 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 0.0): The dropout ratio for the attention probabilities. activation_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for activations inside the fully connected layer. max_position_embeddings (`int`, *optional*, defaults to 128): 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). init_std (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. encoder_layerdrop (`float`, *optional*, defaults to 0.0): The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556) for more details. decoder_layerdrop (`float`, *optional*, defaults to 0.0): The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556) for more details. scale_embedding (`bool`, *optional*, defaults to `False`): Scale embeddings by diving by sqrt(d_model). use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models) forced_eos_token_id (`int`, *optional*, defaults to 2): The id of the token to force as the last generated token when `max_length` is reached. Usually set to `eos_token_id`. Example: ```python >>> from transformers import BlenderbotConfig, BlenderbotModel >>> # Initializing a Blenderbot facebook/blenderbot-3B style configuration >>> configuration = BlenderbotConfig() >>> # Initializing a model (with random weights) from the facebook/blenderbot-3B style configuration >>> model = BlenderbotModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` blenderbotpast_key_valuesencoder_attention_headsd_model)num_attention_heads hidden_sizec ||_||_||_||_||_||_||_||_||_||_ ||_ ||_ ||_ ||_ | |_||_| |_| |_| |_||_||_||_||_||_||_t3|hd| ||d|y)N)is_encoder_decoderencoder_no_repeat_ngram_sizeforced_eos_token_id) is_decodertie_word_embeddings vocab_sizemax_position_embeddingsr encoder_ffn_dimencoder_layersr decoder_ffn_dimdecoder_layersdecoder_attention_headsdropoutattention_dropoutactivation_dropoutactivation_functioninit_stdencoder_layerdropdecoder_layerdrop use_cachenum_hidden_layersscale_embedding pad_token_id bos_token_id eos_token_iddecoder_start_token_idsuper__init__)selfrrrrr rrrr r!r"rrr rrrrr(r$r%r&r'rrrrkwargs __class__s i/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/blenderbot/configuration_blenderbot.pyr*zBlenderbotConfig.__init__cs>%#6 $'>$ .,'>$.,'>$ !2"4#6   !2!2"!/.(((&<#  1)E 3   )iH( r2r3r5TTgelui g?r5r5g{Gz?Fr7r1rr1FT) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_mapr* __classcell__)r-s@r.rrsE NJ#4"5,EV_`M # " "" %& 9> > r/rN) r<configuration_utilsrutilsr get_loggerr9loggerr__all__rr/r.rFs>%3   H %J 'J Z  r/