
    Uh'                     J   d dl mZmZmZmZ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 dd	l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#m$Z$m%Z% ddl&m'Z'  e$       rd dl(m)Z) ddl*m+Z+  e%jX                  e-      Z. G d dej^                        Z0 G d dej^                        Z1 G d dej^                        Z2dejf                  de4dejf                  fdZ5	 d5dej^                  dejf                  d ejf                  d!ejf                  d"eejf                     d#e6d$e6fd%Z7d& Z8d6d'Z9 G d( d)ej^                        Z: G d* d+e      Z;e" G d, d-e             Z<e" G d. d/e<             Z= G d0 d1ee!      Z>e" G d2 d3e<e             Z?g d4Z@y)7    )CallableListOptionalTupleUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)AttentionMaskConverter)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)
LossKwargsauto_docstringcan_return_tupleis_torch_flex_attn_availablelogging   )CohereConfig)	BlockMask)make_flex_block_causal_maskc                   &     e Zd Zd fd	Zd Z xZS )CohereLayerNormc                     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)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizeepsbias	__class__s       |/var/www/catia.catastroantioquia-mas.com/valormas/lib/python3.12/site-packages/transformers/models/cohere/modeling_cohere.pyr%   zCohereLayerNorm.__init__;   s/    ll5::k#:; #    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 )NT)keepdim   )	dtypetor'   float32meanpowrsqrtr*   r)   )r+   hidden_statesinput_dtyper9   variances        r0   forwardzCohereLayerNorm.forwardA   s    #))%((7!!"d!3!D(--a055b$5G&-XH]H]=]1^^u}}5E,,r1   )Ngh㈵>F__name__
__module____qualname__r%   r?   __classcell__r/   s   @r0   r"   r"   :   s    $-r1   r"   c                   ^     e Zd Zddef fdZ ej                         ed               Z xZ	S )CohereRotaryEmbeddingconfigc                    t         |           t        |d      rG|j                  ;|j                  j	                  d|j                  j	                  d            | _        nd| _        |j                  | _        |j                  | _        || _	        t        | j
                     | _        | j                  | j                  |      \  }| _        | j                  d|d       | j                  | _        y )Nrope_scaling	rope_typetypedefaultinv_freqF)
persistent)r$   r%   hasattrrJ   getrK   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrH   r   rope_init_fnattention_scalingregister_bufferrN   original_inv_freq)r+   rH   devicerN   r/   s       r0   r%   zCohereRotaryEmbedding.__init__L   s    6>*v/B/B/N#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r1   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        j                  |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   r3   r   mpscpuF)device_typeenabledr5   dimr6   )rN   floatexpandshape
isinstancerY   rL   strr'   autocast	transposerepeat_interleavecosrV   sinr7   r6   )
r+   xposition_idsinv_freq_expandedposition_ids_expandedr]   freqsembrj   rk   s
             r0   r?   zCohereRotaryEmbedding.forward]   sD    !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)
rA   rB   rC   r   r%   r'   no_gradr   r?   rD   rE   s   @r0   rG   rG   K   s3    /| /" U]]_<  <r1   rG   c                   $     e Zd Z fdZd Z xZS )	CohereMLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        y NFr.   )r$   r%   rH   r,   intermediate_sizer   Linear	gate_projup_proj	down_projr
   
hidden_actact_fnr+   rH   r/   s     r0   r%   zCohereMLP.__init__n   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r1   c                     | j                  | j                  | j                  |            | j                  |      z        }|S rr   )r}   r   r{   r|   )r+   rl   r}   s      r0   r?   zCohereMLP.forwardx   s6    NN4;;t~~a/@#ADLLQRO#ST	r1   r@   rE   s   @r0   ru   ru   m   s    0r1   ru   r<   n_repreturnc                     | 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)rd   rc   reshape)r<   r   batchnum_key_value_headsslenhead_dims         r0   	repeat_kvr   }   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr1   modulequerykeyvalueattention_maskscalingdropoutc                 T   t        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
|#|d d d d d d d |j
                  d   f   }|
|z   }
t        j                  j                  |
dt        j                        j                  |j                        }
t        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )Nr5   r	   r3   )r`   r6   )ptrainingr   )r   num_key_value_groupsr'   matmulrh   rd   r   
functionalsoftmaxr8   r7   r6   r   r   
contiguous)r   r   r   r   r   r   r   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r0   eager_attention_forwardr      s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#k1==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r1   c                     | dd d df   }| ddd df   }t        j                  | |gd      j                  d      }|S )N.r5   r   r3   r_   r   )r'   stackflatten)rl   x1x2rot_xs       r0   rotate_halfr      sL    	
3!8B	
319BKK"b	r*2226ELr1   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.
        position_ids (`torch.Tensor`, *optional*):
            Deprecated and unused.
        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.
    ra   )r6   rb   	unsqueezer   r7   )	qkrj   rk   rm   unsqueeze_dimr6   q_embedk_embeds	            r0   apply_rotary_pos_embr      s    ( GGE		A		A
--
&C
--
&C3w;q>C/0G3w;q>C/0G::E:"GJJUJ$;;;r1   c                   >    e Zd ZdZddedee   f fdZ	 	 ddej                  de
ej                  ej                  f   deej                     dee   d	eej                     d
ee   de
ej                  eej                     ee
ej                        f   fdZ xZS )CohereAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrH   	layer_idxc                 h   t         |           || _        || _        t	        |d|j
                  |j                  z        | _        |j                  |j                  z  | _	        | j                  dz  | _
        |j                  | _        d| _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j                  | j                  z  |j
                  |j                        | _        |j(                  | _        | j(                  ret+        |j                  | j                  f|j,                        | _        t+        |j                  | j                  f|j,                        | _        y y )Nr   g      Trx   r,   r-   )r$   r%   rH   r   getattrr,   num_attention_headsr   r   r   r   attention_dropout	is_causalr   rz   attention_biasq_projk_projv_projo_projuse_qk_normr"   layer_norm_epsq_normk_normr+   rH   r   r/   s      r0   r%   zCohereAttention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 "--)#77GVMbMbDK *#77GVMbMbDK r1   r<   position_embeddingsr   past_key_valuecache_positionr   r   c                    |j                   d d }g |d| j                  }| j                  |      j                  |      }	| j	                  |      j                  |      }
| j                  |      j                  |      }| j                  r"| j                  |	      }	| j                  |
      }
|	j                  dd      }	|
j                  dd      }
|j                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  r^| j                  j                  dk(  r(|j!                  dd      rt"        j%                  d	       nt&        | j                  j                     } || |	|
||f| j(                  sd
n| j*                  | j,                  d|\  }} |j.                  g |d j1                         }| j3                  |      }||fS )Nr3   r   r5   )rk   rj   r   eagersdpaoutput_attentionsFz`torch.nn.functional.scaled_dot_product_attention` does not support `output_attentions=True`. Falling back to eager attention. This warning can be removed using the argument `attn_implementation="eager"` when loading the model.        )r   r   )rd   r   r   viewr   r   r   r   r   rh   r   updater   r   rH   _attn_implementationrQ   loggerwarning_oncer   r   r   r   r   r   r   )r+   r<   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rj   rk   cache_kwargsattention_interfacer   r   s                     r0   r?   zCohereAttention.forward   s    $))#2.88b8$--8{{=166|D[[/44\B
{{=166|D;;|4LZ0J#--a3))!Q/
#--a3&S#7jRUWZ#[ j%#&snUL'5'<'<ZW[WeWegs't$J(?;;++w6{{//69fjjI\^c>d##L
 '>dkk>^>^&_#$7	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r1   rr   )NN)rA   rB   rC   __doc__r   r   intr%   r'   Tensorr   r   
LongTensorr   r   r?   rD   rE   s   @r0   r   r      s    G|  J +/597)||7) #5<<#=>7) !.	7)
 !7) !!1!127) -.7) 
u||Xell3XeELL>Q5RR	S7)r1   r   c                   p    e Zd Zdedef fdZ	 	 	 	 	 	 	 ddej                  deej                     deej                     dee
   dee   d	ee   d
eej                     deeej                  ej                  f      dee   deej                  eeej                  ej                  f      f   fdZ xZS )CohereDecoderLayerrH   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        y )N)rH   r   r   )
r$   r%   r,   r   	self_attnru   mlpr"   r   input_layernormr   s      r0   r%   zCohereDecoderLayer.__init__'  sR    !--()LV$.F<N<NU[UjUjkr1   r<   r   rm   r   r   	use_cacher   r   r   r   c	                     |}
| j                  |      } | j                  d||||||||d|	\  }}| j                  |      }|
|z   |z   }|f}|r||f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_value (`Tuple(torch.FloatTensor)`, *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`).
            cache_position (`torch.LongTensor` of shape `(sequence_length)`, *optional*):
                Indices depicting the position of the input sequence tokens in the sequence
            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   rm   r   r   r   r   r    )r   r   r   )r+   r<   r   rm   r   r   r   r   r   r   residualhidden_states_attentionself_attn_weightshidden_states_mlpoutputss                  r0   r?   zCohereDecoderLayer.forward.  s    > !,,]; 6DT^^ 
6
')%)/) 3
6
 
6
2!2 !HH]3 !#::=NN ")++Gr1   )NNNFFNN)rA   rB   rC   r   r   r%   r'   r   r   r   r   boolr   r   r   FloatTensorr?   rD   rE   s   @r0   r   r   &  s   l| l l 2637*.,1$)59KO:||: !.: u//0	:
 !: $D>: D>: !!1!12: &eELL%,,,F&GH: -.: 
u  (51B1BEDUDU1U+V"WW	X:r1   r   c                   F    e Zd ZeZdZdZdgZdgZdZ	dZ
dZdZdZdZdZd Zy)CoherePreTrainedModelmodelTr   past_key_valuesc                    | j                   j                  }t        |t        j                        rY|j
                  j                  j                  d|       |j                  %|j                  j                  j                          y y t        |t        j                        rf|j
                  j                  j                  d|       |j                  2|j
                  j                  |j                     j                          y y t        |t              r&|j
                  j                  j                  d       y y )Nr   )r9   stdg      ?)rH   initializer_rangere   r   rz   r)   datanormal_r.   zero_	Embeddingpadding_idxr"   fill_)r+   r   r   s      r0   _init_weightsz#CoherePreTrainedModel._init_weightsz  s    kk++fbii(MM&&CS&9{{&  &&( '-MM&&CS&9!!-""6#5#56<<> .0MM$$S) 1r1   N)rA   rB   rC   r   config_classbase_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_2_supports_sdpa_supports_flex_attn_supports_cache_class_supports_quantized_cache_supports_static_cache_supports_attention_backendr   r   r1   r0   r   r   k  sS    L&*#-.#4"5!N  $!"&*r1   r   c                       e Zd Zdef fdZd Zd Zee	 	 	 	 	 	 	 	 	 dde	e
j                     de	e
j                     de	e
j                     de	e   d	e	e
j                     d
e	e   de	e   de	e   de	e
j                     dee   defd              Z	 ddee
j                  df   de
j                  de
j                  dedef
dZede
j                  dedede
j0                  de
j                  defd       Z xZS )CohereModelrH   c           	         t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        | j)                          y c c}w )Nr   )rH   F)r$   r%   pad_token_idr   
vocab_sizer   r   r,   embed_tokens
ModuleListrangenum_hidden_layersr   layersr"   r   normrG   
rotary_embgradient_checkpointing	post_initr   s      r0   r%   zCohereModel.__init__  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdy	2d
 $1C1C&J_J_`	/v>&+# 	 es   Dc                     | j                   S rr   r	  r+   s    r0   get_input_embeddingsz CohereModel.get_input_embeddings  s       r1   c                     || _         y rr   r  r+   r   s     r0   set_input_embeddingsz CohereModel.set_input_embeddings  s
    !r1   	input_idsr   rm   r   inputs_embedsr   r   output_hidden_statesr   flash_attn_kwargsr   c
                    ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }|d u |d uz  rt	        d      | j
                  r%| j                  r|rt        j                  d       d}t        |t        d       t        f      st	        d      || j                  |      }|r|
t               }|	F||j                         nd}t        j                   |||j"                  d   z   |j$                        }	||	j'                  d      }| j)                  |||	||      }|}| j+                  ||      }|rdnd }|rdnd }| j,                  d | j                   j.                   D ],  }|r||fz  } ||f||||||	|d	|
}|d   }|s$||d   fz  }. | j1                  |      }|r||fz  }t3        ||r|nd ||
      S )Nz:You must specify exactly one of input_ids or inputs_embedszX`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.FzBThe `past_key_values` should be either a `Cache` object or `None`.r   r   rY   r   )r   rm   r   r   r   r   r   )last_hidden_stater   r<   
attentions)rH   r   r  r   
ValueErrorr  r   r   r   re   rL   r   r	  r   get_seq_lengthr'   arangerd   rY   r   _update_causal_maskr  r  r  r  r   )r+   r  r   rm   r   r  r   r   r  r   r  past_seen_tokensr   r<   r   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r0   r?   zCohereModel.forward  sT    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I /DJ+>?abb  --i8M0*nO!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L..M>?L]
 & #oom\J #7BD0d![[)H4;;+H+HI 	6M#!m%55!)
*)."3#-$7
 $
M *!,M =#3"55'	6* 		-0  -!11&+/8Od+%	
 	
r1   r   input_tensorc           	         | j                   j                  dk(  r||dk(  j                         r|S y | j                   j                  dk(  r't        |t        j
                        rt        |      }|S ||j                         nd}||j                  nd}| j                   j                  dk(  r(|s&|s$t        j                  |||| j                        ry |j                  }|j                  d   }	|r|j                         }
n1t        |t        j
                        r|j                  d	   n||	z   dz   }
| j                  ||	|
|||j                  d   
      }| j                   j                  dk(  rQ|O|j                   j"                  dv r7|s5t	        j$                  |      j&                  }t        j(                  ||      }|S )Nflash_attention_2r   flex_attentionr   Fr   )r  past_key_values_lengthis_trainingr   r3   )sequence_lengthtarget_lengthr6   r   
batch_size)cudaxpunpu)rH   r   anyre   r'   r   r    r"  is_compileabler   _ignore_causal_mask_sdpar   r6   rd   get_max_cache_shape5_prepare_4d_causal_attention_mask_with_cache_positionrY   rL   finfomin_unmask_unattended)r+   r   r*  r   r   r   r%  using_compilable_cacher6   r0  r1  r   	min_dtypes                r0   r$  zCohereModel._update_causal_mask   s    ;;++/BB)~/D.I.I.K%%;;++/??.%,,7!<^!L!!
 @O?Z?99;`aCRC^!?!?di ;;++v5>T]n%>>*'7 MM	 ""&,,Q/!+??AM nell; $$R(%7!;  PP+')#))!, Q 
 KK,,6*%%**.DD%
 E*..I0CCKQZ[Kr1   r0  r1  r6   r2  c                    | | j                         dk(  r| }|S t        j                  |      j                  }t        j                  ||f|||j
                        }|dk7  rt        j                  |d      }|t        j                  ||j
                        |j                  dd      kD  z  }|ddddddf   j                  |ddd      }| |j                         }| j                  d   }	|ddddddd|	f   | ddddddf   j                  |j
                        z   }
|
dk(  }
|ddddddd|	f   j                  |
|      |ddddddd|	f<   |S )	aM  
        Creates a causal 4D mask of shape `(batch_size, 1, query_length, key_value_length)` from a 2D mask of shape
        `(batch_size, key_value_length)`, or if the input `attention_mask` is already 4D, do nothing.

        Args:
            attention_mask (`torch.Tensor`):
                A 2D attention mask of shape `(batch_size, key_value_length)` or a 4D attention mask of shape
                `(batch_size, 1, query_length, key_value_length)`.
            sequence_length (`int`):
                The sequence length being processed.
            target_length (`int`):
                The target length: when generating with static cache, the mask should be as long as the static cache,
                to account for the 0 padding, the part of the cache that is not filled yet.
            dtype (`torch.dtype`):
                The dtype to use for the 4D attention mask.
            cache_position (`torch.Tensor`):
                Indices depicting the position of the input sequence tokens in the sequence.
            batch_size (`torch.Tensor`):
                Batch size.
        N   )
fill_valuer6   rY   r   )diagonalr  r3   r   )r`   r'   r;  r<  fullrY   triur#  r   rc   clonerd   r7   masked_fill)r   r0  r1  r6   r   r2  r   r   r?  mask_lengthpadding_masks              r0   r:  zACohereModel._prepare_4d_causal_attention_mask_with_cache_positionD  s   < %.*<*<*>!*C(K* ' E*..I** -0Ye\j\q\qK !##jjqA5<<n>S>STWeWmWmnprsWtttK%dD!Q&67>>z1bRTUK))//1,2226*1aL[L+@ANSTVZ\`bcScDdDgDg&&E    ,q05@Aq,;,AV5W5c5c )6Aq!\k\12 r1   )	NNNNNNNNN)F)rA   rB   rC   r   r%   r  r  r   r   r   r'   r   r   r   r   r   r   r   r   r?   r   r$  staticmethodr   r6   r:  rD   rE   s   @r0   r  r    s   |  !"  151537+/59$(,0/359\
E,,-\
 !.\
 u//0	\

 "%\
   1 12\
 D>\
 $D>\
 'tn\
 !!1!12\
 $$89\
 
!\
  \
H #(BellK78B llB 	B
 B  BH 444 4 {{	4
 4 4 4r1   r  c                       e Zd Zy)KwargsForCausalLMN)rA   rB   rC   r   r1   r0   rL  rL  |  s    r1   rL  c                       e Zd ZdgZddiZddgdgfiZ fdZd Zd Zd	 Z	d
 Z
d Zd Zee	 	 	 	 	 	 	 	 	 	 	 ddeej"                     deej$                     deej"                     deeeeej,                     f      deej,                     deej"                     dee   dee   dee   deej"                     deeej$                  f   dee   defd              Z xZS )CohereForCausalLMzlm_head.weightlm_headcolwise_repr<   logitsc                 ,   t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        |j                  | _	        |j                  | _
        | j                          y rw   )r$   r%   r  r   r  r   rz   r,   rO  logit_scaletie_word_embeddingsr  r   s     r0   r%   zCohereForCausalLM.__init__  sq      (
 ++yy!3!3V5F5FUS!--#)#=#=  	r1   c                 .    | j                   j                  S rr   r   r	  r  s    r0   r  z&CohereForCausalLM.get_input_embeddings  s    zz&&&r1   c                 &    || j                   _        y rr   rV  r  s     r0   r  z&CohereForCausalLM.set_input_embeddings  s    "'

r1   c                     | j                   S rr   rO  r  s    r0   get_output_embeddingsz'CohereForCausalLM.get_output_embeddings  s    ||r1   c                     || _         y rr   rY  )r+   new_embeddingss     r0   set_output_embeddingsz'CohereForCausalLM.set_output_embeddings  s	    %r1   c                     || _         y rr   r   )r+   decoders     r0   set_decoderzCohereForCausalLM.set_decoder  s	    
r1   c                     | j                   S rr   r_  r  s    r0   get_decoderzCohereForCausalLM.get_decoder  s    zzr1   r  r   rm   r   r  labelsr   r   r  r   logits_to_keepr   r   c                    ||n| j                   j                  }|	|	n| j                   j                  }	 | 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 )az  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

        Example:

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

        >> model = CohereForCausalLM.from_pretrained("CohereForAI/c4ai-command-r-v01")
        >> tokenizer = AutoTokenizer.from_pretrained("CohereForAI/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."
        ```N)	r  r   rm   r   r  r   r   r  r   )rQ  rd  r  )lossrQ  r   r<   r   r   )rH   r   r  r   r  re   r   slicerO  rS  loss_functionr  r   r   r<   r   )r+   r  r   rm   r   r  rd  r   r   r  r   re  r   r   r<   slice_indicesrQ  rg  s                     r0   r?   zCohereForCausalLM.forward  s+   N 2C1N-TXT_T_TqTq$8$D $++JjJj 	
 ,64:: ,
)%+'/!5),
 ,
  118B>SV8W~ot4]kmA}a,?@A$***%4%%pVFt{{OeOepiopD%#33!//))
 	
r1   )NNNNNNNNNNr   )rA   rB   rC   _tied_weights_keys_tp_plan_pp_planr%   r  r  rZ  r]  ra  rc  r   r   r   r'   r   r   r   r   r   r   r   r   r   rL  r   r?   rD   rE   s   @r0   rN  rN    s   *+=)H_-z:;H	'(&  151537KO59-1$(,0/35934H
E,,-H
 !.H
 u//0	H

 "%tE4E4E/F(F"GHH
   1 12H
 ))*H
 D>H
 $D>H
 'tnH
 !!1!12H
 c5<</0H
 *+H
 
 H
  H
r1   rN  )rN  r  r   )r   )Nr   )Atypingr   r   r   r   r   r'   r   activationsr
   cache_utilsr   r   
generationr   modeling_attn_mask_utilsr   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   r   configuration_coherer   !torch.nn.attention.flex_attentionr   integrations.flex_attentionr    
get_loggerrA   r   Moduler"   rG   ru   r   r   r   rb   r   r   r   r   r   r   r  rL  rN  __all__r   r1   r0   <module>r     s  < : 9   ! . ) > B 9 O K F & h h .  !;J 
		H	%-bii -"<BII <D		  	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % %4<<Z)bii Z)zB3 BJ *O * *8 p' p pf ?,j > l
- l
 l
^ Hr1   