o -i%&@s:dZddlmZddlmZeeZGdddeZdS)zNemotron model configuration)PretrainedConfig)loggingcs\eZdZdZdZdgZ            dfdd ZddZZS)NemotronConfiga This is the configuration class to store the configuration of a [`NemotronModel`]. It is used to instantiate a Nemotron 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 Nemotron-8B. 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 Nemotron model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`NemotronModel`] hidden_size (`int`, *optional*, defaults to 6144): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 24576): 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 48): Number of attention heads for each attention layer in the Transformer decoder. head_dim (`int`, *optional*): Projection weights dimension in multi-head attention. Set to hidden_size // num_attention_heads if None num_key_value_heads (`int`, *optional*): 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 `num_attention_heads`. hidden_act (`str` or `function`, *optional*, defaults to `"relu2"`): The non-linear activation function (function or string) in the decoder. max_position_embeddings (`int`, *optional*, defaults to 4096): The maximum sequence length that this model might ever be used with. initializer_range (`float`, *optional*, defaults to 0.0134): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the 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*): Padding token id. bos_token_id (`int`, *optional*, defaults to 2): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 3): End of stream token id. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings rope_parameters (`dict`, *optional*): The parameters of the RoPE embeddings. Expected contents: `rope_theta` (`float`): The base period of the RoPE embeddings. `rope_type` (`str`): The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope', 'llama3'], with 'default' being the original RoPE implementation. `partial_rotary_factor` (`float`, *optional*, defaults to 0.5): Percentage of the query and keys which will have rotary embedding. 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 0.0): The dropout ratio for the attention probabilities. mlp_bias (`bool`, *optional*, defaults to `False`): Whether to use a bias in up_proj and down_proj layers in the MLP layers. ```python >>> from transformers import NemotronModel, NemotronConfig >>> # Initializing a Nemotron nemotron-15b style configuration >>> configuration = NemotronConfig() >>> # Initializing a model from the nemotron-15b style configuration >>> model = NemotronModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```nemotronpast_key_values` 0Nrelu2S!uq?h㈵>TFc s||_| |_||_||_||_||_|p|d}|dur|n|||_|dur*|}||_||_ | |_ | |_ | |_ | dd}|pF|pFddi}| dd}d|vrU||d<|dpe|dpe|d ped }d |vrn||d <||_|||_||_||_tjd | |||d |dS) N kv_channels rope_scaling rope_typedefault rope_thetag@ rope_percentrope_percentagepartial_rotary_factorg?) pad_token_id bos_token_id eos_token_idtie_word_embeddings) vocab_sizemax_position_embeddings hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsgethead_dimnum_key_value_heads hidden_actinitializer_rangenorm_eps use_cachepoprope_parameters_rope_parameters_validationattention_biasattention_dropoutmlp_biassuper__init__)selfr r"r#r$r%r'r(r)r!r*r+r,rrrrr.r0r1r2kwargsrrr __class__re/home/ubuntu/veenaModal/venv/lib/python3.10/site-packages/vllm/transformers_utils/configs/nemotron.pyr4zsV    zNemotronConfig.__init__cCs|jdurdS|jdd}|jdd}|dvr td||dkr<|dur,tdt|tr5|dkr>td |dSdS) z? Validate the `rope_parameters` configuration. Nrfactor>linearrdynamiczA`rope_type` must be one of ['default', 'linear', 'dynamic'], got rz]If `rope_type` is not 'default', `rope_parameters` must include a `factor` field. Got `None`.g?z:`rope_parameters`'s factor field must be a float > 1, got )r.r& ValueError isinstancefloat)r5rr:rrr9r/s. z*NemotronConfig._rope_parameters_validation)rrr r r NNr r rrTNrrFNFrF) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencer4r/ __classcell__rrr7r9rs4\IrN) rC transformersrtransformers.utilsr get_loggerr@loggerrrrrr9s