o
    ei"                     @   s2   d dl mZ d dlmZ G dd deZdgZdS )   )PreTrainedConfig)RopeParametersc                *       s<  e Zd ZdZdZdgZddddddddZdgdgfd	d
gd	gfd	gd	gfdZ																				d3dedB dedB dedB d edB d!edB d"edB d#edB d$e	dB d%edB d&e
dB d'edB d(edB d)edB d*edB d+edB d,edB d-eee	ef B dB d.edB d/e
dB d0edB f( fd1d2Z  ZS )4GemmaConfiga  
    This is the configuration class to store the configuration of a [`GemmaModel`]. It is used to instantiate an Gemma
    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 Gemma-7B.
    e.g. [google/gemma-7b](https://huggingface.co/google/gemma-7b)
    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 256000):
            Vocabulary size of the Gemma model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`GemmaModel`]
        hidden_size (`int`, *optional*, defaults to 3072):
            Dimension of the hidden representations.
        intermediate_size (`int`, *optional*, defaults to 24576):
            Dimension of the MLP representations.
        num_hidden_layers (`int`, *optional*, defaults to 28):
            Number of hidden layers in the Transformer decoder.
        num_attention_heads (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer decoder.
        num_key_value_heads (`int`, *optional*, defaults to 16):
            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`.
        head_dim (`int`, *optional*, defaults to 256):
            The attention head dimension.
        hidden_act (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`):
            The legacy activation function. It is overwritten by the `hidden_activation`.
        max_position_embeddings (`int`, *optional*, defaults to 8192):
            The maximum sequence length that this model might ever be used with.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
            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 0):
            Padding token id.
        eos_token_id (`int`, *optional*, defaults to 1):
            End of stream token id.
        bos_token_id (`int`, *optional*, defaults to 2):
            Beginning of stream token id.
        tie_word_embeddings (`bool`, *optional*, defaults to `True`):
            Whether to tie weight embeddings
        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`.
        attention_bias (`bool`, defaults to `False`, *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 0.0):
            The dropout ratio for the attention probabilities.
        use_bidirectional_attention (`bool`, *optional*):
            If True, the model will attend to all text tokens instead of using a causal mask.

    ```python
    >>> from transformers import GemmaModel, GemmaConfig
    >>> # Initializing a Gemma gemma-7b style configuration
    >>> configuration = GemmaConfig()
    >>> # Initializing a model from the gemma-7b style configuration
    >>> model = GemmaModel(configuration)
    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```gemmapast_key_valuescolwiserowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_proj	input_idsinputs_embedshidden_statesattention_mask)embed_tokenslayersnorm      `           gelu_pytorch_tanh    {Gz?ư>T          NF        
vocab_sizehidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsnum_key_value_headshead_dim
hidden_actmax_position_embeddingsinitializer_rangerms_norm_eps	use_cachepad_token_ideos_token_idbos_token_idtie_word_embeddingsrope_parametersattention_biasattention_dropoutuse_bidirectional_attentionc                    s   || _ |	| _|| _|| _|| _|| _|| _|| _|| _|
| _	|| _
|| _|| _|| _|| _|| _|| _|| _|| _|| _t jdi | d S )N )r   r&   r   r    r!   r"   r$   r#   r%   r'   r(   r)   r/   r0   r1   r*   r,   r+   r-   r.   super__init__)selfr   r   r    r!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r+   r,   r-   r.   r/   r0   r1   kwargs	__class__r2   k/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/gemma/configuration_gemma.pyr4   q   s*   zGemmaConfig.__init__)r   r   r   r   r   r   r   r   r   r   r   Tr   r   r   TNFr   N)__name__
__module____qualname____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planintstrfloatboolr   dictr4   __classcell__r2   r2   r7   r9   r      s    F


	
r   N)configuration_utilsr   modeling_rope_utilsr   r   __all__r2   r2   r2   r9   <module>   s
    
	