Pg,hdZddlZddlmZddlmZej eZGddeZ dgZ y)zZamba model configurationN)PretrainedConfig)loggingcveZdZdZdZdgZ dfd ZdZxZS) ZambaConfiga1 This is the configuration class to store the configuration of a [`ZambaModel`]. It is used to instantiate a Zamba 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 Zamba-v0.1 model. [Zyphra/Zamba-7B-v1](https://huggingface.co/Zyphra/Zamba-7B-v1) 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 32000): Vocabulary size of the Zamba model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`ZambaModel`] tie_word_embeddings (`bool`, *optional*, defaults to `True`): 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 3712): Dimension of the hidden representations. attention_hidden_size (`int`, *optional*): Dimension of the hidden representations of the inputs to the Attention layer. intermediate_size (`int`, *optional*, defaults to 14848): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 76): Number of hidden layers in the model. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer decoder. attention_head_dim (`int`, *optional*): Dimension of the attention head 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=None`, 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). n_mamba_heads (`int`, *optional*, defaults to 2): Number of mamba heads for each mamba layer. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the decoder. hidden_mamba_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the mamba layer. 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-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`. 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. 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. max_position_embeddings (`int`, *optional*, defaults to 4096): 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. attn_layer_period (`int`, *optional*, defaults to 6): Once in this many layers, we will have a shared attention layer attn_layer_offset (`int`, *optional*, defaults to 4): Offset of the shared attention 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 mamba discretization projection matrix. `"auto"` means that it will default to `math.ceil(self.hidden_size / 16)` time_step_min (`float`, *optional*, defaults to 0.001): Minimum `time_step` used to bound `dt_proj_bias`. time_step_max (`float`, *optional*, defaults to 0.1): Maximum `time_step` used to bound `dt_proj_bias`. time_step_floor (`float`, *optional*, defaults to 0.0001): Minimum clamping value of the `dt_proj.bias` layer initialization. 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 zambapast_key_valuesc" ||_||_||_| d|z|_n||_||_||_||_|"d|jz|j z|_n||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_||_||_||_||_||_||_|dk(r"t1j2|jdz n||_||_||_||_| |_|!|_|jA||||_!|j.|jz|jzdk(sJdtE#|d||||d|"y)Nautorz;`intermediate_size` should be divisible by `n_mamba_heads`.) pad_token_id bos_token_id eos_token_idtie_word_embeddings)$ vocab_sizer hidden_sizeattention_hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsattention_head_dimmax_position_embeddingsattention_dropoutnum_key_value_heads n_mamba_heads hidden_acthidden_mamba_actinitializer_range rms_norm_eps use_cachenum_logits_to_keepattn_layer_periodattn_layer_offsetuse_mamba_kernels mamba_d_state mamba_d_conv mamba_expandmathceil mamba_dt_rank time_step_min time_step_maxtime_step_floormamba_conv_biasmamba_proj_bias_layers_block_typelayers_block_typesuper__init__)$selfrrrrrrrrrrrrr r!r"r#rrrrrr$r%r&r'r(r)r,r-r.r/r0r1kwargs __class__s$ t/var/www/html/suriana-translation/venv/lib/python3.12/site-packages/transformers/models/zamba/configuration_zamba.pyr5zZambaConfig.__init__~sJ%#6 & ()*[D &)>D &!2!2#6  %&'$*:*:&:d>V>V&VD #&8D #'>$!2#6 *$ 0!2(""4!2!2!2*((ANRXAXTYYt'7'7"'<=^k**...!%!8!89JL]_p!q    0 0 0   "#$ c%b c$  %%% 3    cfgdt|dz Dcgc]}||z|k(rdndc}z}|Scc}w)N)mambar<hybridrr=r<)range)r6rr$r%ilayerss r9r2zZambaConfig._layers_block_typesN [``qtu`uZv wUV..2CCX P w x   xs.)!i}TiNi:Lr Nr r gelusilug{Gz?gh㈵>TrrDr igTr rFr r gMbP?g?g-C6?TF) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencer5r2 __classcell__)r8s@r9rrs^@J#4"5 " $EZ xr:r) rJr*configuration_utilsrutilsr get_loggerrGloggerr__all__rr:r9rSs@ 3   H %F"FR /r: