id0ddlZddlmZddlmZmZddlmZddlmZm Z ddl m Z ddl m Z dd lmZdd lmZmZdd lmZdd lmZd dlmZd dlmZmZmZmZmZmZm Z m!Z!m"Z"m#Z#m$Z$GddeeZ%Gdde Z&GddeZ'Gdde#Z(GddeZ)Gdde"Z*Gdde$Z+Gdde!Z,Gd d!eZ-Gd"d#eZ.Gd$d%eZ/Gd&d'eZ0gd(Z1y))N)nn)Cache DynamicCache)PreTrainedConfig)create_causal_mask!create_sliding_window_causal_mask)BaseModelOutputWithPast)RopeParameters)Unpack)TransformersKwargsauto_docstring)merge_with_config_defaults)capture_outputs) MistralConfig) Qwen2AttentionQwen2DecoderLayerQwen2ForCausalLMQwen2ForQuestionAnsweringQwen2ForSequenceClassificationQwen2ForTokenClassificationQwen2MLP Qwen2ModelQwen2PreTrainedModel Qwen2RMSNormQwen2RotaryEmbeddingc*eZdZdZdZ ddedzdedzdedzdedzdedzd edzd edzd edzd edzd edzdedzdedzdedzdedzdedzdedzde dzdedzdedzde edzf(dZ y)MinistralConfiga 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 ``` ministralN 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 | |_||_||_||_||_| |_||_||_||_||_ ||_ ||_ ||}||_ ||_ | |_| |_| |_||_||_|j$|jdndg|z|_||_t)j*|fi|y)Nsliding_attentionfull_attention)r-r.r/r0r!r)r"r#r$r%r2r'r&r(r*r+r,r3r4r1r__init__)selfr!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r0r1r2r3r4kwargss k/mnt/e/genesis-system/.venv/lib/python3.12/site-packages/transformers/models/ministral/modular_ministral.pyr8zMinistralConfig.__init__ms0)((#6 $'>$&!2!2#6 ,    &"5 #6 $!2("!2&    #'+':':'F#L\ ! "D  /!!$1&1)i}i8 r>Nsiluig{Gz?gư>TNrFNr=gN) __name__ __module__ __qualname____doc__ model_typeintstrfloatboolr listr8r<r;rrsoK ZJ"'"&(-(**,*+#!'.7*.%)!%#'#$#$+015%)*-(,+82$J824Z82: 82 : 82 !4Z 82!4Z82*82$J82"%t82!4<82dl82$;82Dj82Dj82 Dj!82""D[#82$($.%82&d '82(!4<)82*#Y%+82r<rc eZdZy) MinistralMLPNrBrCrDrLr<r;rNrNr<rNc$eZdZdeffd ZxZS)MinistralAttention layer_idxct|||tj|j|j |j zd|_tj|j|j|j zd|_ tj|j|j|j zd|_ y)NF)bias) superr8rLinearr"r%r'q_projr&k_projv_proj)r9configrS __class__s r;r8zMinistralAttention.__init__s +ii 2 2F4N4NQUQ^Q^4^ejk ii 2 2F4N4NQUQ^Q^4^ejk ii 2 2F4N4NQUQ^Q^4^ejk r<)rBrCrDrGr8 __classcell__r\s@r;rRrRsl#llr<rRc eZdZy)MinistralRMSNormNrOrLr<r;r`r`rPr<r`c eZdZy)MinistralDecoderLayerNrOrLr<r;rbrbrPr<rbc eZdZy)MinistralPreTrainedModelNrOrLr<r;rdrdrPr<rdc eZdZy)MinistralRotaryEmbeddingNrOrLr<r;rfrfrPr<rfceZdZdeffd Zeee ddejdzdejdzdejdzde dzdejdzd e dzd ejdzd eed efd ZxZS)MinistralModelr[c(t|||`y)N)rVr8has_sliding_layers)r9r[r\s r;r8zMinistralModel.__init__s   #r<N input_idsattention_mask position_idspast_key_values inputs_embedsr,cache_positionr:returnc |du|duz r td||j|}|r|t|j}|F||j nd} t j | | |jdz|j}||jd}t|x} ts*|j|||||d} td i| td i| d} |} |j| |} |jd|jj D]}|| f| |j"||||| d|} !|j%| } t'| |r| Sd S) Nz:You must specify exactly one of input_ids or inputs_embeds)r[rrA)device)r[rorlrprnrm)r7r6)rlrmrnr,rpposition_embeddings)last_hidden_staternrL) ValueError embed_tokensrr[get_seq_lengthtorcharangeshapers unsqueeze isinstancedictrr rotary_emblayersr$attention_typenormr )r9rkrlrmrnror,rpr:past_seen_tokenscausal_mask_mapping mask_kwargs hidden_statesrt decoder_layers r;forwardzMinistralModel.forwards  -t"; <YZ Z   --i8M 0*$++>O  !CRC^==?de "\\ "2]5H5H5K"KTaThThN  )33A6L?-F++!."0"0#2 , K#5"C{"C%F%U%U#  & "oom\J![[)H4;;+H+HI M) 2=3O3OP) /#-$7  M  -0 &+/8O  >B  r<)NNNNNNN)rBrCrDrr8rrrry LongTensorTensorr FloatTensorrJr r r rr]r^s@r;rhrhs$$ .2.204(,26!%26A ##d*A  t+A &&- A  A ((4/ A $;A ((4/A +,A  !A  A r<rhc eZdZy)MinistralForCausalLMNrOrLr<r;rrrPr<rc eZdZy)"MinistralForSequenceClassificationNrOrLr<r;rrrPr<rc eZdZy)MinistralForTokenClassificationNrOrLr<r;rrrPr<rc eZdZy)MinistralForQuestionAnsweringNrOrLr<r;rrrPr<r)rrdrhrrrr)2ryr cache_utilsrrconfiguration_utilsr masking_utilsrr modeling_outputsr modeling_rope_utilsr processing_utilsr utilsr r utils.genericrutils.output_capturingrmistral.configuration_mistralrqwen2.modeling_qwen2rrrrrrrrrrrrrNrRr`rbrdrfrhrrrr__all__rLr<r;rs .3R71&7759    H2m%5H2V 8 ll |  -  3  3 I ZI X +  )G  &A  $=  r<