qi4fddlmZddlmZGddeZGddeZGddeZgd Zy ) )PreTrainedConfig)RopeParametersceZdZdZdZdZddddddddgd d dgd d d fdededededededededeededeededede ffd Z xZ S)Emu3VQVAEConfiga This is the configuration class to store the configuration of a [`Emu3VQVAE`]. It is used to instantiate an VQ-VAE model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a configuration to the VQ model presented in Emu3 paper. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: codebook_size (`int`, *optional*, defaults to 32768): Codebook size of the VQ model. embed_dim (`int`, *optional*, defaults to 4): Dimension of the quantized vector in codebook. latent_channels (`int`, *optional*, defaults to 4): Dimension of the output channel of encoder and the input channel of decoder double_latent (`bool`, *optional*, defaults to `False`): Whether double the output dim of the encoder. in_channels (`int`, *optional*, defaults to 3): Input channel of encoder. out_channels (`int`, *optional*, defaults to 3): Output channel of decoder. temporal_downsample_factor (`int`, *optional*, defaults to 4): Temporal downsample factor. base_channels (`int`, *optional*, defaults to 256): Basic channel number of the intermediate blocks. channel_multiplier (`list[int]`, *optional*, defaults to `[1, 2, 2, 4]`): Channel scaling factor of the intermediate blocks. num_res_blocks (`int`, *optional*, defaults to 2): Residual block number in each stage. attn_resolutions (`list[int]`, *optional*, defaults to `[3]`): Stage indices to apply attention. hidden_size (`int`, *optional*, defaults to 1024): Dimension of the hidden representations in the attention layer. num_attention_heads (`int`, *optional*, defaults to 1): Number of attention heads for each attention layer. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. ```python >>> from transformers import Emu3VQVAE, Emu3VQVAEConfig >>> # Initializing a video VQ model of Emu3 configuration >>> configuration = Emu3VQVAEConfig() >>> # Initializing a model from the Emu3 VQ model style configuration >>> model = Emu3VQVAE(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` emu3_vqgan vq_configiFr)r r r ir g codebook_size embed_dimlatent_channels double_latent in_channels out_channelstemporal_downsample_factor base_channelschannel_multipliernum_res_blocksattn_resolutions hidden_sizenum_attention_headsattention_dropoutc t|di|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_yN)super__init__r rrrrrrrrrrrrr)selfr rrrrrrrrrrrrrkwargs __class__s ]/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/emu3/configuration_emu3.pyrzEmu3VQVAEConfig.__init__Ks$ "6"*".*&(*D'*"4, 0&#6 !2) __name__ __module__ __qualname____doc__ model_typebase_config_keyintboollistfloatr __classcell__r"s@r#rrs0 dJ!O# #*+ (4'(c#$#&!3!3!3 !3  !3  !3!3%(!3!3!I!3!3s)!3!3!!3!!3!3r$rc$eZdZdZdZdZdgZdZ ddeded ed ed ed edzd e dede de dededede dzde de de dzf"fd Z xZS)Emu3TextConfiga This is the configuration class to store the configuration of a [`Emu3TextModel`]. It is used to instantiate a emu3 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 [Emu3-community/Emu3-Chat-hf](https://huggingface.co/Emu3-community/Emu3-Chat-hf). 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 184622): Vocabulary size of the Emu3 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Emu3Model`] hidden_size (`int`, *optional*, defaults to 4096): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 14336): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 32): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 32): Number of attention heads for each attention layer in the Transformer decoder. num_key_value_heads (`int`, *optional*, defaults to 8): This is the number of key_value heads that should be used to implement Grouped Query Attention. If `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details, check out [this paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to `num_attention_heads`. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the decoder. max_position_embeddings (`int`, *optional*, defaults to 9216): The maximum sequence length that this model might ever be used with. Emu supports up to 9216 tokens, rms_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the rms normalization layers. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. pad_token_id (`int`, *optional*, defaults to 151643): Padding token id. bos_token_id (`int`, *optional*, defaults to 151849): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 151850): End of stream token id. rope_parameters (`RopeParameters`, *optional*): Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE with longer `max_position_embeddings`. mlp_bias (`bool`, *optional*, defaults to `False`): Whether to use a bias in up_proj, down_proj and gate_proj layers in the MLP layers. attention_bias (`bool`, *optional*, defaults to `False`): Whether to use a bias in the query, key, value and output projection layers during self-attention. attention_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings ```python >>> from transformers import Emu3Model, Emu3Config >>> # Initializing a Emu3-community/Emu3-Chat-hf style configuration >>> configuration = Emu3Config() >>> # Initializing a model from the Emu3-community/Emu3-Chat-hf style configuration >>> model = Emu3Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```emu3_text_model text_configpast_key_valuesg.AN vocab_sizerintermediate_sizenum_hidden_layersrnum_key_value_heads hidden_actmax_position_embeddings rms_norm_eps use_cache pad_token_id bos_token_id eos_token_idrope_parametersrinitializer_rangetie_word_embeddingsc .||_||_||_||_||_||_||_||_| |_| |_ ||_ ||_ ||_ ||_ ||_| |_| |_| |_||_t'|Pdi|yr)r6r;rr7r8rr9r:r<r=mlp_biasattention_biasrBrrAr>r?r@rCrr)r r6rr7r8rr9r:r;r<r=r>r?r@rArErFrrBrCr!r"s r#rzEmu3TextConfig.__init__s.%'>$&!2!2#6 #6 $("  ,!2!2.(((#6  "6"r$)i.ii8 rGsilui$gh㈵>Ti[Pi)Qi*QNFFg?g{Gz?F)r%r&r'r(r)r*keys_to_ignore_at_inference default_thetar+strr.r,rrr/r0s@r#r2r2osH T#J#O#4"5M!!&!##%*+ '+""""15#&#'+0)+#+#+# +#  +# ! +#!4Z+#+#"%+#+#+#+#+#+#($.+#$!%+#&!'+#("D[)+#+#r$r2c teZdZdZdZdgZeedZ d de ezde ezde e e fdzd e dzffd Z xZ S) Emu3Configa This is the configuration class to store the configuration of a [`Emu3Model`]. It is used to instantiate a emu3 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 [Emu3-community/Emu3-Chat-hf](https://huggingface.co/Emu3-community/Emu3-Chat-hf). Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: vq_config (`Union[Dict, Emu3VQVAEConfig]`, *optional*): Emu3VQVAEConfig instance containing the configuration for the VQ-VAE model. text_config (`Union[Dict, Emu3TextConfig]``, *optional*): Emu3TextConfig instance containing the configuration for the language model. vocabulary_map (`dict`, *optional*): A dictionary containing the vocabulary map from the tokenizer. Used to obtain tokens from the image inputs. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings emu3r5)r4rNrr4vocabulary_maprCc 0| t}nt|tr tdi|}| t}nt|tr tdi|}||_||_||_||jdnd|_||_ t|,di|y)Nzr) r isinstancedictr2rr4rPgetimage_token_idrCrr)r rr4rPrCr!r"s r#rzEmu3Config.__init__s  ')I  4 ('4)4I  (*K  T *(7;7K"&,?M?Yn00;_c#6  "6"r$)NNNF)r%r&r'r(r)rJr2r sub_configsrSr+r,rr/r0s@r#rNrNs{*J#4"5"0OK-1-104+0 #/)#N*#S#X- # "D[ ##r$rN)rNr2rN)configuration_utilsrmodeling_rope_utilsrrr2rN__all__rr$r#rZsB"41W3&W3t{#%{#|2#!2#j >r$