
    ^j`X                        d dl mZ d dlmZ d dlZd dlmZ ddlmZ ddl	m
Z
mZ ddlmZ ddlmZmZ dd	lmZ dd
lmZmZ ddlmZmZ ddlmZmZ ddlmZ ddlmZm Z m!Z! ddl"m#Z#m$Z$ ddl%m&Z& ddl'm(Z(  G d dejR                        Z* G d dejR                        Z+dejX                  de-dejX                  fdZ.	 d3dejR                  dejX                  dejX                  dejX                  dejX                  dz  d e/d!e/d"ee   fd#Z0d$ Z1d4d%Z2 G d& d'ejR                        Z3 G d( d)ejR                        Z4 G d* d+e      Z5e  G d, d-e             Z6e  G d. d/e6             Z7e  G d0 d1e6e             Z8g d2Z9y)5    )Callable)OptionalN   )ACT2FN)CacheDynamicCache)GenerationMixin)create_causal_mask!create_sliding_window_causal_mask)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs   )Cohere2Configc                        e Zd ZU ej                  ed<   ddef fdZe	 	 	 ddedz  de	d   de
dz  ded	ef   fd
       Z ej                         ed               Z xZS )Cohere2RotaryEmbeddinginv_freqNconfigc                    t         |           |j                  | _        |j                  | _        || _        | j
                  j                  d   | _        | j                  }| j                  dk7  rt        | j                     } || j
                  |      \  }| _
        | j                  d|d       | j                  d|j                         d       y )N	rope_typedefaultr   F)
persistentoriginal_inv_freq)super__init__max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr   rope_parametersr!   compute_default_rope_parametersr   attention_scalingregister_bufferclone)selfr   devicerope_init_fnr   	__class__s        w/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/cohere2/modeling_cohere2.pyr&   zCohere2RotaryEmbedding.__init__-   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuU    r0   ztorch.deviceseq_lenreturnztorch.Tensorc                    | j                   d   }t        | dd      xs | j                  | j                  z  }d}d|t	        j
                  d|dt        j                        j                  |t        j                        |z  z  z  }||fS )	a  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        
rope_thetahead_dimNg      ?r      dtype)r0   r<   )	r*   getattrhidden_sizenum_attention_headstorcharangeint64tofloat)r   r0   r5   basedimattention_factorr   s          r3   r+   z6Cohere2RotaryEmbedding.compute_default_rope_parameters=   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r4   c                    | j                   d d d d f   j                         j                  |j                  d   dd      }|d d d d d f   j                         }t	        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  |dd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j                  |j                   
      	j                  |j                   
      fS # 1 sw Y   AxY w)Nr   r   mpscpuF)device_typeenabledr:   rF   r;   )r   rD   expandshape
isinstancer0   typestrr   	transposer@   repeat_interleavecosr,   sinrC   r<   )
r/   xposition_idsinv_freq_expandedposition_ids_expandedrL   freqsembrV   rW   s
             r3   forwardzCohere2RotaryEmbedding.forward[   s@    !MM$4-8>>@GGHZHZ[\H]_acde ,QaZ 8 > > @'1!((--'E!((--[`J`ahhmmfkUC 	5&,,.1F1L1L1NNYYZ[]^_E))%;C'')d444C'')d444C		5 vvAGGv$cff177f&;;;	5 	5s   =BFF
N)NNN)__name__
__module____qualname__r@   Tensor__annotations__r   r&   staticmethodr   inttuplerD   r+   no_gradr   r^   __classcell__r2   s   @r3   r   r   *   s    llV} V  '++/"*$*(* t* 
~u$	%	* *: U]]_<  <r4   r   c                   &     e Zd Zd fd	Zd Z xZS )Cohere2LayerNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)zcThe hidden size can be a tuple or an int. The tuple is used for QKNorm to normalize across head_dimN)r%   r&   nn	Parameterr@   onesweightvariance_epsilon)r/   r>   epsbiasr2   s       r3   r&   zCohere2LayerNorm.__init__l   s/    ll5::k#:; #r4   c                    |j                   }|j                  t        j                        }|j	                  dd      }||z
  j                  d      j	                  dd      }||z
  t        j                  || j                  z         z  }| j                  j                  t        j                        |z  }|j                  |      S )NrI   T)keepdimr:   )	r<   rC   r@   float32meanpowrsqrtrr   rq   )r/   hidden_statesinput_dtyperx   variances        r3   r^   zCohere2LayerNorm.forwardr   s    #))%((7!!"d!3!D(--a055b$5G&-XH]H]=]1^^u}}5E,,r4   )Ngh㈵>Fr`   ra   rb   r&   r^   ri   rj   s   @r3   rl   rl   k   s    $-r4   rl   r{   n_repr6   c                     | j                   \  }}}}|dk(  r| S | dddddddddf   j                  |||||      } | j                  |||z  ||      S )z
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r   N)rP   rO   reshape)r{   r   batchnum_key_value_headsslenr9   s         r3   	repeat_kvr   |   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr4   modulequerykeyvalueattention_maskscalingdropoutkwargsc                    t        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
||
|z   }
t
        j                  j                  |
dt        j                        j                  |j                        }
t
        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )Nr:   r   rI   )rF   r<   )ptrainingr   )r   num_key_value_groupsr@   matmulrT   rn   
functionalsoftmaxrw   rC   r<   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r3   eager_attention_forwardr      s     3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!#n4==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r4   c                     | dd d df   }| ddd df   }t        j                  | |gd      j                  d      }|S )N.r:   r   rI   rN   )r@   stackflatten)rX   x1x2rot_xs       r3   rotate_halfr      sL    	
3!8B	
319BKK"b	r*2226ELr4   c                 6   | j                   }| j                         } |j                         }|j                  |      }|j                  |      }| |z  t        |       |z  z   }||z  t        |      |z  z   }|j	                  |      |j	                  |      fS )a  Applies Rotary Position Embedding to the query and key tensors.

    Args:
        q (`torch.Tensor`): The query tensor.
        k (`torch.Tensor`): The key tensor.
        cos (`torch.Tensor`): The cosine part of the rotary embedding.
        sin (`torch.Tensor`): The sine part of the rotary embedding.
        unsqueeze_dim (`int`, *optional*, defaults to 1):
            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
    Returns:
        `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
    r;   )r<   rD   	unsqueezer   rC   )qkrV   rW   unsqueeze_dimr<   q_embedk_embeds           r3   apply_rotary_pos_embr      s    $ GGE		A		A
--
&C
--
&C3w;q>C/0G3w;q>C/0G::E:"GJJUJ$;;;r4   c                       e Zd ZdZddededz  f fdZ	 ddej                  de	ej                  ej                  f   dej                  dz  d	e
dz  d
ee   de	ej                  ej                  dz  e	ej                     dz  f   fdZ xZS )Cohere2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperNr   	layer_idxc                    t         |           || _        || _        t	        |d|j
                  |j                  z        | _        |j                  |j                  z  | _	        | j                  dz  | _
        |j                  | _        d| _        |j                  |   dk(  r|j                  nd | _        t        j                   |j
                  |j                  | j                  z  |j"                        | _        t        j                   |j
                  |j                  | j                  z  |j"                        | _        t        j                   |j
                  |j                  | j                  z  |j"                        | _        t        j                   |j                  | j                  z  |j
                  |j"                        | _        y )Nr9   g      Tsliding_attentionrt   )r%   r&   r   r   r=   r>   r?   r9   r   r   r   attention_dropout	is_causallayer_typessliding_windowrn   Linearattention_biasq_projk_projv_projo_projr/   r   r   r2   s      r3   r&   zCohere2Attention.__init__   sq   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!97=7I7I)7TXk7kf33quii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r4   r{   position_embeddingsr   past_key_valuesr   r6   c                 8   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
|\  }}| j                  t        ||	||      \  }}	| |j                  |	|
| j                        \  }	}
t        j                  | j                  j                  t              } || ||	|
|f| j                   sdn| j"                  | j$                  | j                  d|\  }} |j&                  g |d j)                         }| j+                  |      }||fS )NrI   r   r:           )r   r   r   )rP   r9   r   viewrT   r   r   r   r   updater   r   get_interfacer   _attn_implementationr   r   r   r   r   r   r   )r/   r{   r   r   r   r   input_shapehidden_shapequery_statesr   r   rV   rW   attention_interfacer   r   s                   r3   r^   zCohere2Attention.forward   s    $))#2.88b8$--8{{=166|DNNqRST[[/44\BLLQPQR
{{=166|DNNqRST&S*';L*VY[^'_$L*&'6'='=j,X\XfXf'g$J(?(M(MKK,,.E)
 %8
%
  $}}C$2H2HLL..
%
 
%
!\ *k));;;;FFHkk+.L((r4   r_   )r`   ra   rb   __doc__r   rf   r&   r@   rc   rg   r   r   r   r^   ri   rj   s   @r3   r   r      s    G
} 
t 
: )-()||() #5<<#=>() t+	()
 () +,() 
u||U\\D0%2E2LL	M()r4   r   c                   $     e Zd Z fdZd Z xZS )
Cohere2MLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        y NFr   )r%   r&   r   r>   intermediate_sizern   r   	gate_projup_proj	down_projr   
hidden_actact_fnr/   r   r2   s     r3   r&   zCohere2MLP.__init__  s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r4   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r_   )r   r   r   r   )r/   rX   r   s      r3   r^   zCohere2MLP.forward  s6    NN4;;t~~a/@#ADLLQRO#ST	r4   r~   rj   s   @r3   r   r     s    0r4   r   c                   $    e Zd Zdedef fdZ	 	 	 	 ddej                  deej                  ej                  f   dz  dej                  dz  de	dz  d	e
dz  d
ee   deej                  eej                  ej                  f   dz  f   fdZ xZS )Cohere2DecoderLayerr   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        y )N)r   r   r>   rs   )
r%   r&   r>   r   	self_attnr   mlprl   layer_norm_epsinput_layernormr   s      r3   r&   zCohere2DecoderLayer.__init__  sR    !--)9Mf%/V=O=OV\VkVklr4   Nr{   r   r   r   	use_cacher   r6   c           	          |}| j                  |      } | j                  d|||||d|\  }}	| j                  |      }
||z   |
z   }|S )a  
        Args:
            hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
            attention_mask (`torch.FloatTensor`, *optional*):
                attention mask of size `(batch_size, sequence_length)` if flash attention is used or `(batch_size, 1,
                query_sequence_length, key_sequence_length)` if default attention is used.
            past_key_values (`Cache`, *optional*): cached past key and value projection states
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
            use_cache (`bool`, *optional*):
                If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
                (see `past_key_values`).
            position_embeddings (`tuple[torch.FloatTensor, torch.FloatTensor]`, *optional*):
                Tuple containing the cosine and sine positional embeddings of shape `(batch_size, seq_len, head_dim)`,
                with `head_dim` being the embedding dimension of each attention head.
        )r{   r   r   r   r    )r   r   r   )r/   r{   r   r   r   r   r   residualhidden_states_attention_hidden_states_mlps              r3   r^   zCohere2DecoderLayer.forward#  su    4 !,,];%3T^^ &
' 3)+&
 &
" !HH]3 #::=NNr4   )NNNF)r`   ra   rb   r   rf   r&   r@   rc   rg   r   boolr   r   FloatTensorr^   ri   rj   s   @r3   r   r     s    m} m m IM.2(,!&'||' #5<<#=>E' t+	'
 ' $;' +,' 
u  %(9(95;L;L(L"MPT"TT	U'r4   r   c                   J    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZy)Cohere2PreTrainedModelr   modelTr   r   )r{   
attentionsN)r`   ra   rb   r   rd   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr   r4   r3   r   r   M  sQ    &*#./#4"5N!"&,&r4   r   c                        e Zd Zdef fdZeee	 	 	 	 	 	 ddej                  dz  dej                  dz  dej                  dz  dedz  dej                  dz  d	edz  d
ee   defd                     Z xZS )Cohere2Modelr   c           	      
   t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        | j)                          y c c}w )Nr   F)r%   r&   pad_token_idpadding_idx
vocab_sizern   	Embeddingr>   embed_tokens
ModuleListrangenum_hidden_layersr   layersrl   r   normr   
rotary_embgradient_checkpointing	post_initr   s      r3   r&   zCohere2Model.__init__b  s     !.. ++LL):):F<N<NPTP`P`ammEJ6KcKcEde	 3e
 %&2D2D6K`K`a	08&+# 	 fs   D N	input_idsr   rY   r   inputs_embedsr   r   r6   c           
         |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|V||j	                         nd}t        j                  |j                  d   |j                        |z   }|j                  d      }t        |x}	t              s)| j                  ||||d}
t        d
i |
t        d
i |
d}	|}| j                  ||      }t        | j                         D ].  \  }} ||f|	| j                  j"                  |      ||||d|}0 | j%                  |      }t'        ||	      S )Nz:You must specify exactly one of input_ids or inputs_embeds)r   r   r   )r0   )r   r  r   r   rY   )full_attentionr   )r   r   r   r   rY   )last_hidden_stater   r   )
ValueErrorr   r   r   get_seq_lengthr@   rA   rP   r0   r   rQ   dictr
   r   r  	enumerater   r   r   r   )r/   r  r   rY   r   r  r   r   past_seen_tokenscausal_mask_mappingmask_kwargsr{   r   idecoder_layers                  r3   r^   zCohere2Model.forwardq  s    -t";<YZZ  --i8M0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L?-F++!."0#2 ,K #5"C{"C%F%U%U#
 &"oom\J )$++ 6 		A})24;;3J3J13MN$7 /#) M		 		-0&++
 	
r4   )NNNNNN)r`   ra   rb   r   r&   r   r   r   r@   
LongTensorrc   r   r   r   r   r   r   r^   ri   rj   s   @r3   r   r   `  s    }    .2.204(,26!%7
##d*7
 t+7
 &&-	7

 7
 ((4/7
 $;7
 +,7
 
!7
    7
r4   r   c                   B    e Zd ZddiZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 dd	e	j                  dz  d
e	j                  dz  de	j                  dz  dedz  de	j                  dz  de	j                  dz  dedz  dee	j                  z  dee   defd              Z xZS )Cohere2ForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr{   logitsc                 ,   t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        |j                  | _	        |j                  | _
        | j                          y r   )r%   r&   r   r   r   rn   r   r>   r  logit_scaletie_word_embeddingsr  r   s     r3   r&   zCohere2ForCausalLM.__init__  sq     !&)
 ++yy!3!3V5F5FUS!--#)#=#=  	r4   Nr  r   rY   r   r  labelsr   logits_to_keepr   r6   c	           
          | j                   d||||||d|	}
|
j                  }t        |t              rt	        | d      n|}| j                  |dd|ddf         }|| j                  z  }d}|* | j                  d||| j                  j                  d|	}t        |||
j                  |
j                  |
j                        S )a  
        Example:

        ```python
        >> from transformers import AutoTokenizer, Cohere2ForCausalLM

        >> model = Cohere2ForCausalLM.from_pretrained("Cohere2ForAI/c4ai-command-r-v01")
        >> tokenizer = AutoTokenizer.from_pretrained("Cohere2ForAI/c4ai-command-r-v01")

        >> prompt = "Hey, are you conscious? Can you talk to me?"
        >> inputs = tokenizer(prompt, return_tensors="pt")

        >> # Generate
        >> generate_ids = model.generate(inputs.input_ids, max_length=30)
        >> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
        ```)r  r   rY   r   r  r   N)r  r  r   )lossr  r   r{   r   r   )r   r  rQ   rf   slicer  r  loss_functionr   r   r   r   r{   r   )r/   r  r   rY   r   r  r  r   r  r   outputsr{   slice_indicesr  r  s                  r3   r^   zCohere2ForCausalLM.forward  s    > ,64:: ,
)%+',
 ,
  118B>SV8W~ot4]kmA}a,?@A$***%4%%pVFt{{OeOepiopD%#33!//))
 	
r4   )NNNNNNNr   )r`   ra   rb   _tied_weights_keys_tp_plan_pp_planr&   r   r   r@   r  rc   r   r   r   rf   r   r   r   r^   ri   rj   s   @r3   r  r    s   *,GH23H_-z:;H	  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
r4   r  )r  r   r   )r   )r   ):collections.abcr   typingr   r@   torch.nnrn   activationsr   cache_utilsr   r   
generationr	   masking_utilsr
   r   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.output_capturingr   configuration_cohere2r   Moduler   rl   rc   rf   r   rD   r   r   r   r   r   r   r   r   r  __all__r   r4   r3   <module>r8     s  * %    ! . ) R 9 O K F & I I G 5 0><RYY ><B-ryy -"	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2<8C)ryy C)L  /4 /d _  $ J
) J
 J
Z H
/ H
 H
V Kr4   