o ei`"@s2ddlmZddlmZGdddeZdgZdS))PreTrainedConfig)RopeParametersc*s4eZdZdZdZdgZddddddddZdgdgfd d gd gfd gd gfd Z                 d1dedBdedBdedBdedBdedBd edBd!edBd"e dBd#edBd$e dBd%e dBd&e dBd'edBd(edBd)edBd*e dBd+e dBd,edBd-e dBd.e e dBf(fd/d0 ZZS)2MinistralConfiga This is the configuration class to store the configuration of a [`MinistralModel`]. It is used to instantiate an Ministral 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 Ministral-8B-Instruct-2410. [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410) [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410) 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 Ministral model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`MinistralModel`] 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, check out [this paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to `8`. head_dim (`int`, *optional*, defaults to `hidden_size // num_attention_heads`): The attention head dimension. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the decoder. max_position_embeddings (`int`, *optional*, defaults to `4096*32`): The maximum sequence length that this model might ever be used with. Ministral's sliding window attention allows sequence of up to 4096*32 tokens. 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*): 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. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether the model's input and output word embeddings should be tied. 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`. sliding_window (`int`, *optional*, defaults to 4096): Sliding window attention window size. If not specified, will default to `4096`. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. layer_types (`list`, *optional*): Attention pattern for each layer. ```python >>> from transformers import MinistralModel, MinistralConfig >>> # Initializing a Ministral 8B style configuration >>> configuration = MinistralConfig() >>> # Initializing a model from the Ministral 8B style configuration >>> model = MinistralModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` ministralpast_key_valuescolwiserowwise)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_proj input_ids inputs_embeds hidden_statesattention_mask) embed_tokenslayersnorm}8 Nsilu{Gz?ư>TF vocab_size hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsnum_key_value_headshead_dim hidden_actmax_position_embeddingsinitializer_range rms_norm_eps use_cache pad_token_id bos_token_id eos_token_idtie_word_embeddingsrope_parameterssliding_windowattention_dropout layer_typesc s| |_||_||_||_||_| |_||_||_||_||_ ||_ ||_ |dur*|}||_ ||_ | |_| |_| |_||_||_|jdurQ|j durKdndg||_||_tjdi|dS)Nsliding_attentionfull_attention)r(r)r*r+rr$rrrr r-r"r!r#r%r&r'r.r/r,super__init__)selfrrrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/kwargs __class__r2s/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/ministral/configuration_ministral.pyr4ks8 zMinistralConfig.__init__)rrrrrrNrrrrTNrrFNrrN)__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planintstrfloatboolrlistr4 __classcell__r2r2r7r9r sM        rN)configuration_utilsrmodeling_rope_utilsrr__all__r2r2r2r9s