
    g-                     f    d Z ddlZddlmZ ddlmZ  ej        e          Z G d de          Z	dS )zJamba model configuration    N   )PretrainedConfig)loggingc                        e Zd ZdZdZdgZ	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 d fd	Zed             Zed             Z	de
dedefdZ xZS ) JambaConfiga,  
    This is the configuration class to store the configuration of a [`JambaModel`]. It is used to instantiate a
    Jamba 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 Jamba-v0.1 model.

    [ai21labs/Jamba-v0.1](https://huggingface.co/ai21labs/Jamba-v0.1)

    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 65536):
            Vocabulary size of the Jamba model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`JambaModel`]
        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
            Whether the model's input and output word embeddings should be tied. Note that this is only relevant if the
            model has a output word embedding layer.
        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 encoder.
        num_attention_heads (`int`, *optional*, defaults to 32):
            Number of attention heads for each attention layer in the Transformer encoder.
        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 checkout [this
            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `8`.
        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
            The non-linear activation function (function or string) in the decoder.
        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`.
        num_logits_to_keep (`int` or `None`, *optional*, defaults to 1):
            Number of prompt logits to calculate during generation. If `None`, all logits will be calculated. If an
            integer value, only last `num_logits_to_keep` logits will be calculated. Default is 1 because only the
            logits of the last prompt token are needed for generation. For long sequences, the logits for the entire
            sequence may use a lot of memory so, setting `num_logits_to_keep=1` will reduce memory footprint
            significantly.
        output_router_logits (`bool`, *optional*, defaults to `False`):
            Whether or not the router logits should be returned by the model. Enabling this will also
            allow the model to output the auxiliary loss. See [here]() for more details
        router_aux_loss_coef (`float`, *optional*, defaults to 0.001):
            The aux loss factor for the total loss.
        pad_token_id (`int`, *optional*, defaults to 0):
            The id of the padding token.
        bos_token_id (`int`, *optional*, defaults to 1):
            The id of the "beginning-of-sequence" token.
        eos_token_id (`int`, *optional*, defaults to 2):
            The id of the "end-of-sequence" token.
        sliding_window (`int`, *optional*):
            Sliding window attention window size. If not specified, will default to `None`.
        max_position_embeddings (`int`, *optional*, defaults to 262144):
            This value doesn't have any real effect. The maximum sequence length that this model is intended to be
            used with. It can be used with longer sequences, but performance may degrade.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        num_experts_per_tok (`int`, *optional*, defaults to 2):
            The number of experts to root per-token, can be also interpreted as the `top-p` routing
            parameter
        num_experts (`int`, *optional*, defaults to 16):
            Number of experts per Sparse MLP layer.
        expert_layer_period (`int`, *optional*, defaults to 2):
            Once in this many layers, we will have an expert layer
        expert_layer_offset (`int`, *optional*, defaults to 1):
            The first layer index that contains an expert mlp layer
        attn_layer_period (`int`, *optional*, defaults to 8):
            Once in this many layers, we will have a vanilla attention layer
        attn_layer_offset (`int`, *optional*, defaults to 4):
            The first layer index that contains a vanilla attention mlp layer
        use_mamba_kernels (`bool`, *optional*, defaults to `True`):
            Flag indicating whether or not to use the fast mamba kernels. These are available only if `mamba-ssm` and
            `causal-conv1d` are installed, and the mamba modules are running on a CUDA device. Raises ValueError if
            `True` and kernels are not available
        mamba_d_state (`int`, *optional*, defaults to 16):
            The dimension the mamba state space latents
        mamba_d_conv (`int`, *optional*, defaults to 4):
            The size of the mamba convolution kernel
        mamba_expand (`int`, *optional*, defaults to 2):
            Expanding factor (relative to hidden_size) used to determine the mamba intermediate size
        mamba_dt_rank (`Union[int,str]`, *optional*, defaults to `"auto"`):
            Rank of the the mamba discretization projection matrix. `"auto"` means that it will default to `math.ceil(self.hidden_size / 16)`
        mamba_conv_bias (`bool`, *optional*, defaults to `True`):
            Flag indicating whether or not to use bias in the convolution layer of the mamba mixer block.
        mamba_proj_bias (`bool`, *optional*, defaults to `False`):
            Flag indicating whether or not to use bias in the input and output projections (["in_proj", "out_proj"]) of the mamba mixer block

    jambapast_key_values   F    8         silu{Gz?ư>T   MbP?r      N                 autoc"                    || _         || _        || _        || _        || _        || _        || _        || _        || _        ||}|| _	        || _
        |	| _        |
| _        || _        || _        || _        || _        || _        || _        || _        || _        || _        || _        |                     d| j        | j                   |                     d| j        | j                   || _        || _        || _        || _        |dk    rt9          j        | j        dz            n|| _        | | _        |!| _          tC                      j"        d||||d|" d S )N	attentionexpertr   r   )pad_token_idbos_token_ideos_token_idtie_word_embeddings )#
vocab_sizer    hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headssliding_windowmax_position_embeddingsattention_dropoutnum_key_value_heads
hidden_actinitializer_rangerms_norm_eps	use_cachenum_logits_to_keepoutput_router_logitsrouter_aux_loss_coefnum_experts_per_toknum_expertsexpert_layer_periodexpert_layer_offsetattn_layer_periodattn_layer_offset_check_supported_offsetuse_mamba_kernelsmamba_d_statemamba_d_convmamba_expandmathceilmamba_dt_rankmamba_conv_biasmamba_proj_biassuper__init__)$selfr"   r    r#   r$   r%   r&   r*   r+   r,   r-   r.   r/   r0   r1   r   r   r   r'   r(   r)   r2   r3   r4   r5   r6   r7   r9   r:   r;   r<   r?   r@   rA   kwargs	__class__s$                                      i/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/jamba/configuration_jamba.pyrC   zJambaConfig.__init__   s   J %#6 &!2!2#6 ,'>$!2 &"5#6 $!2(""4$8!$8!#6 &#6 #6 !2!2$$[$2H$J`aaa$$Xt/GIabbb!2*((ANRXAXAXTYt'7"'<===^k.. 	
%%% 3		
 	

 	
 	
 	
 	
 	
    c                 D      fdt           j                  D             S )Nc                 >    g | ]}|j         z  j        k    rd ndS )r   mamba)r6   r7   .0irD   s     rG   
<listcomp>z1JambaConfig.layers_block_type.<locals>.<listcomp>   sC     
 
 
 t559OOOKKU\
 
 
rH   ranger%   rD   s   `rG   layers_block_typezJambaConfig.layers_block_type   9    
 
 
 
4122
 
 
 	
rH   c                 D      fdt           j                  D             S )Nc                 H    g | ]}|j         z  j        k    rj        nd S )r   )r4   r5   r3   rL   s     rG   rO   z2JambaConfig.layers_num_experts.<locals>.<listcomp>   sG     
 
 
 !"D$< <@X X XD^_
 
 
rH   rP   rR   s   `rG   layers_num_expertszJambaConfig.layers_num_experts   rT   rH   	property_periodoffsetc           
      H    ||k    rt          | d| d| d| d          d S )Nz layer offset (z) must be smaller than z layer period ())
ValueError)rD   rX   rY   rZ   s       rG   r8   z#JambaConfig._check_supported_offset   sL    VooVooIooflooo   rH   )!r
   Fr   r   r   r   r   r   r   r   Tr   Fr   r   r   r   Nr   r   r   r   r   r   r   r   Tr   r   r   r   TF)__name__
__module____qualname____doc__
model_typekeys_to_ignore_at_inferencerC   propertyrS   rW   strintr8   __classcell__)rF   s   @rG   r   r      s&       ` `D J#4"5 !"" &EU
 U
 U
 U
 U
 U
n 
 
 X
 
 
 X
 c 3        rH   r   )
ra   r=   configuration_utilsr   utilsr   
get_loggerr^   loggerr   r!   rH   rG   <module>rl      s        3 3 3 3 3 3       
	H	%	%O O O O O" O O O O OrH   