o Zhj$@s&ddlmZGdddeZdgZdS))PretrainedConfigcseZdZdZdZdgZddddddddZdgdgfd d gd gfd gd gfd Z                     !d$fd"d# ZZ S)% Gemma2Configa This is the configuration class to store the configuration of a [`Gemma2Model`]. It is used to instantiate an Gemma2 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 Gemma2-7B. e.g. [google/gemma2-7b](https://huggingface.co/google/gemma2-7b) 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 Gemma2 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Gemma2Model`] hidden_size (`int`, *optional*, defaults to 2304): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 9216): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 26): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 8): Number of attention heads for each attention layer in the Transformer decoder. num_key_value_heads (`int`, *optional*, defaults to 4): 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`. head_dim (`int`, *optional*, defaults to 256): The attention head dimension. hidden_activation (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`): The non-linear activation function (function or string) in the decoder. Will default to `"gelu_pytorch_tanh"` if not specified. `"gelu_pytorch_tanh"` uses an approximation of the `"gelu"` activation function. 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_theta (`float`, *optional*, defaults to 10000.0): The base period of the RoPE 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. query_pre_attn_scalar (`float`, *optional*, defaults to 256): scaling factor used on the attention scores sliding_window (`int`, *optional*, defaults to 4096): in Gemma2, every other layer uses sliding window attention. This is the size of the sliding window. final_logit_softcapping (`float`, *optional*, defaults to 30.0): scaling factor when applying tanh softcapping on the logits. attn_logit_softcapping (`float`, *optional*, defaults to 50.0): scaling factor when applying tanh softcapping on the attention scores. cache_implementation (`str`, *optional*, defaults to `"hybrid"`): the cache type to be used with `generate`. ```python >>> from transformers import Gemma2Model, Gemma2Config >>> # Initializing a Gemma2 gemma2-7b style configuration >>> configuration = Gemma2Config() >>> # Initializing a model from the gemma2-7b style configuration >>> model = Gemma2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zgemma2Zpast_key_valuesZcolwiseZrowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projZ input_idsZ inputs_embedsZ hidden_statesZattention_mask)Z embed_tokensZlayersZnorm $gelu_pytorch_tanh {Gz?ư>T@F>@I@hybridc stjd| |||d|||_| |_||_||_||_||_||_||_ | |_ | |_ | |_ ||_ ||_||_||_||_||_||_||_||_dS)N) pad_token_id bos_token_id eos_token_idtie_word_embeddings)super__init__ vocab_sizemax_position_embeddings hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headshead_dimnum_key_value_headsinitializer_range rms_norm_eps use_cache rope_thetaattention_biasattention_dropouthidden_activationquery_pre_attn_scalarsliding_windowfinal_logit_softcappingattn_logit_softcappingcache_implementation)selfrr!r"r#r$r&r%r-r r'r(r)rrrrr*r+r,r.r/r0r1r2kwargs __class__r^/var/www/auris/lib/python3.10/site-packages/transformers/models/gemma2/configuration_gemma2.pyrss8 zGemma2Config.__init__)rrrrrr r r r r rTrrrTrFrr rrrr) __name__ __module__ __qualname____doc__Z model_typeZkeys_to_ignore_at_inferenceZbase_model_tp_planZbase_model_pp_planr __classcell__rrr5r7rsRH  rN)Zconfiguration_utilsrr__all__rrrr7s