rhPddlZddlmZmZddlZddlmZddlmZm Z ddl m Z m Z ddl mZmZddlmZddlmZdd lmZdd lmZdd lmZdd lmZmZd dlmZmZm Z m!Z!m"Z"m#Z#m$Z$m%Z%d dl&m'Z'ejPe)Z*Gdde Z+Gdde#Z,Gdde!Z-Gddeej\Z/GddeZ0Gdde"Z1Gdde'Z2Gdde Z3gd Z4y)!N)CallableOptional)Cache DynamicCache)PretrainedConfiglayer_type_validation)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs)BaseModelOutputWithPast)rope_config_validation)ALL_ATTENTION_FUNCTIONS)Unpack)TransformersKwargslogging)CohereAttentionCohereDecoderLayerCohereForCausalLMCohereLayerNormCoherePreTrainedModelCohereRotaryEmbeddingapply_rotary_pos_embeager_attention_forward) Gemma2ModelceZdZdZdZdgZddddddddZdgdgfd d gd gfd gd gfd Z dfd Ze d Z e jdZ xZ S) Cohere2Configa2 This is the configuration class to store the configuration of a [`CohereModel`]. It is used to instantiate an Cohere model according to the specified arguments, defining the model architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Instantiating a configuration with the defaults will yield a similar configuration to that of the [CohereForAI/c4ai-command-r-v01](https://huggingface.co/CohereForAI/c4ai-command-r-v01) model. Args: vocab_size (`int`, *optional*, defaults to 256000): Vocabulary size of the Cohere model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`CohereModel`] hidden_size (`int`, *optional*, defaults to 8192): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 22528): Dimension of the MLP representations. logit_scale (`float`, *optional*, defaults to 0.0625): The scaling factor for the output logits. num_hidden_layers (`int`, *optional*, defaults to 40): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 64): Number of attention heads for each attention layer in the Transformer decoder. 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, check out [this paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to `num_attention_heads`. 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 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. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization. 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. bos_token_id (`int`, *optional*, defaults to 5): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 255001): End 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. rope_scaling (`Dict`, *optional*): Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value accordingly. Expected contents: `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. `factor` (`float`, *optional*): Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In most scaling types, a `factor` of x will enable the model to handle sequences of length x * original maximum pre-trained length. `original_max_position_embeddings` (`int`, *optional*): Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during pretraining. `attention_factor` (`float`, *optional*): Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention computation. If unspecified, it defaults to value recommended by the implementation, using the `factor` field to infer the suggested value. `beta_fast` (`float`, *optional*): Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear ramp function. If unspecified, it defaults to 32. `beta_slow` (`float`, *optional*): Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear ramp function. If unspecified, it defaults to 1. `short_factor` (`list[float]`, *optional*): Only used with 'longrope'. The scaling factor to be applied to short contexts (< `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden size divided by the number of attention heads divided by 2 `long_factor` (`list[float]`, *optional*): Only used with 'longrope'. The scaling factor to be applied to long contexts (< `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden size divided by the number of attention heads divided by 2 `low_freq_factor` (`float`, *optional*): Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE `high_freq_factor` (`float`, *optional*): Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE 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. sliding_window (`int`, *optional*, defaults to 4096): Size of the sliding window attention context. layer_types (`list`, *optional*): Attention pattern for each layer. ```python >>> from transformers import Cohere2Model, Cohere2Config >>> # Initializing a Cohere Nextmodel configuration >>> configuration = Cohere2Config() >>> # Initializing a model from the Cohere2 configuration >>> model = Cohere2Model(configuration) # doctest: +SKIP >>> # Accessing the model configuration >>> configuration = model.config # doctest: +SKIP ``` cohere2past_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_tokenslayersnormc ||_| |_||_||_||_||_||_||}||_||_| |_ | |_ | |_ ||_ ||_ ||_||_||_||_||z|_t'|t)|Td| |||d||j-dd|_|j"Wt1|dd|_t3|j Dcgc]!}t5|dz|j.zrdnd#c}|_t7|j"ycc}w)N) pad_token_id bos_token_id eos_token_idtie_word_embeddingssliding_window_patternsliding_attentionfull_attention) vocab_sizemax_position_embeddings hidden_size logit_scaleintermediate_sizenum_hidden_layersnum_attention_headsnum_key_value_heads hidden_actinitializer_rangelayer_norm_eps use_cache rope_theta rope_scalingattention_biasattention_dropoutsliding_window layer_typeshead_dimrsuper__init__get_sliding_window_patterngetattrrangeboolr )selfr5r7r9r8r:r;r<r=r6r>r?r@r+r,r-r.rArBrCrDrErFkwargsi __class__s ~/var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/cohere2/modular_cohere2.pyrIzCohere2Config.__init__sm4%'>$&&!2!2#6   &"5 #6 $!2,"$(,!2,&#'::  t$  %%% 3    (.zz2JA'N$    #+249QST+UD (t556 (,QUd6R6R,R'S#Yii D  d../  s9&D=cNtjdt|jS)NzTThe `sliding_window_pattern` attribute is deprecated and will be removed in v4.55.0.)warningswarn FutureWarningrK)rOs rSr/z$Cohere2Config.sliding_window_patterns" b  +++c||_yN)rK)rOvalues rSr/z$Cohere2Config.sliding_window_patterns ',$rX)i iXg?(@Nsilur\g{Gz?gh㈵>TriTg@NFiN) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planrIpropertyr/setter __classcell__rRs@rSrr/sn`J#4"5%.%.%.%."+ )"+&(9:#%568IJ!"_$56  $ /I0V,,""-#-rXrc eZdZy)Cohere2RotaryEmbeddingNrbrcrdr4rXrSroro rXroc eZdZy)Cohere2LayerNormNrpr4rXrSrsrs rqrXrsc2eZdZdZddedeefdZ ddejde ejejfdeejd ee d eejd e ed e ejeejee ejffd Zy)Cohere2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperNconfig layer_idxctjj||_||_t |d|j |jz|_|j|jz|_ |jdz|_ |j|_ d|_ |j|dk(r |jnd|_tj |j |j|jz|j"|_tj |j |j|jz|j"|_tj |j |j|jz|j"|_tj |j|jz|j |j"|_y)NrGgTr2)bias)nnModulerIrvrwrLr7r;rGr<num_key_value_groupsscalingrD is_causalrFrELinearrCq_projk_projv_projo_proj)rOrvrws rSrIzCohere2Attention.__init__su  " F4F4F&JdJd4de $*$>$>&B\B\$\!}}d* !'!9!97=7I7I)7TXk7kf33quii    : :T]] JQWQfQf  ii    : :T]] JQWQfQf  ii    : :T]] JQWQfQf  ii  & & 68J8JQWQfQf  rXr%position_embeddingsr&past_key_valuecache_positionrPreturnc b|jdd}g|d|j}|j|j|j dd} |j |j|j dd} |j |j|j dd} |\} } |jt| | | | \} } |'| | |d}|j| | |j|\} } t}|jjdk7rt|jj}||| | | |f|jsdn |j |j"|jd|\}}|j$g|dj'}|j)|}||fS)Nr1r)sincosreagerra)dropoutr}rE)shaperGrview transposerrrErupdaterwrrv_attn_implementationrtrainingrDr}reshape contiguousr)rOr%rr&rrrP input_shape hidden_shape query_states key_states value_statesrr cache_kwargsattention_interface attn_output attn_weightss rSforwardzCohere2Attention.forward,s$))#2. 88b8$--8 {{=166|DNNqRST [[/44\BLLQPQR {{=166|DNNqRST &S    *';L*VY[^'_ $L*  %#&snUL'5'<'*)!. *) ! *) !!1!12 *)-.*) u||Xell3XeELL>Q5RR S*)rXruc<eZdZdedeffd Z d dejdeejejfde ejde e de e d e ejd e ed eeje eejejfffd ZxZS)Cohere2DecoderLayerrvrwcNt||||j||_yrZ)rHrIrFattention_type)rOrvrwrRs rSrIzCohere2DecoderLayer.__init__Zs% +$00;rXr%rr&rr@rrPrc |}|j|}|jd||||||d|\} } |j|} || z| z}|S)N)r%rr&rr@rr4)input_layernorm self_attnmlp) rOr%rr&rr@rrPresidualhidden_states_attention_hidden_states_mlps rSrzCohere2DecoderLayer.forward^sx!,,]; %3T^^& ' 3))) & & "!HH]3 #::=NN rX)NNFN)rbrcrdrrrIrrrrrrNrrr FloatTensorrrlrms@rSrrYs<}<<26*.$)59||#5<<#=>!.  !  D> !!1!12-. u  (51B1BEDUDU1U+V"WW XrXrceZdZUeed<y)Cohere2PreTrainedModelrvN)rbrcrdr__annotations__r4rXrSrrys rXrceZdZdeffd Z d deejdeejdeejdee deejdee d eejd e e d efd ZxZS) Cohere2Modelrvct||t|j|j|_t ||_y)N)r7eps)rv)rHrIrsr7r?r)ro rotary_emb)rOrvrRs rSrIzCohere2Model.__init__~s6  $&2D2D6K`K`a 0?rXr#r& position_idsr r$r@rrPrc p|du|duz r td||j|}|r||js t}|F||j nd} t j | | |jdz|j}||jd}t|x} ts*|j|||||d} td i| td i| d} |} |j| |} |j D]}|| f| | |j"|||d|} |j%| } t'| |S) Nz:You must specify exactly one of input_ids or inputs_embedsrr1)device)rv input_embedsr&rr r)r3r2)rr&rr@r)last_hidden_stater r4) ValueErrorr'rrget_seq_lengthrarangerr unsqueeze isinstancedictrvr r rr(rr)r )rOr#r&rr r$r@rrPpast_seen_tokenscausal_mask_mapping mask_kwargsr%r decoder_layers rSrzCohere2Model.forwards  -t"; <YZ Z   --i8M 0*nO  !CRC^==?de "\\ "2]5H5H5K"KTaThThN  )33A6L?-F++ -"0"0#2 , K#5"C{"C%F%U%U#  & "oom\J![[ M)$72=3O3OP.#- M  -0 &++  rX)NNNNNNN)rbrcrdrrIrrrrrrrNrrr rrlrms@rSrr}s@}@151537+/59$(59< E,,-< !.< u//0 < "% <   1 12 < D>< !!1!12< +,<  !< rXrc eZdZy)Cohere2ForCausalLMNrpr4rXrSrrrqrXr)rrrr)5rUtypingrrrtorch.nnrz cache_utilsrrconfiguration_utilsrr masking_utilsr r modeling_flash_attention_utilsr modeling_outputsr modeling_rope_utilsrmodeling_utilsrprocessing_utilsrutilsrrcohere.modeling_cohererrrrrrrrgemma2.modeling_gemma2r get_loggerrbloggerrrorsr{rurrrr__all__r4rXrSrs % .JRB795&0   1   H %W-$W-t 2   E) E)P,@2B ;B J *  \rX