
    fTh'                     \   S SK JrJrJrJrJr  S SKrS SKJr  SSKJ	r	  SSK
JrJr  SSKJr  SSKJr  SS	KJr  SS
KJr  SSKJrJr  SSKJrJr  SSKJrJr  SSKJr  SSK J!r!J"r"J#r#J$r$J%r%  SSK&J'r'  \$" 5       (       a  S SK(J)r)  SSK*J+r+  \%RX                  " \-5      r. " S S\R^                  5      r0 " S S\R^                  5      r1 " S S\R^                  5      r2S\Rf                  S\4S\Rf                  4S jr5 S5S\R^                  S\Rf                  S \Rf                  S!\Rf                  S"\\Rf                     S#\6S$\64S% jjr7S& r8S6S' jr9 " S( S)\R^                  5      r: " S* S+\5      r;\" " S, S-\5      5       r<\" " S. S/\<5      5       r= " S0 S1\\!5      r>\" " S2 S3\<\5      5       r?/ S4Qr@g)7    )CallableListOptionalTupleUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)AttentionMaskConverter)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)
LossKwargsauto_docstringcan_return_tupleis_torch_flex_attn_availablelogging   )CohereConfig)	BlockMask)make_flex_block_causal_maskc                   2   ^  \ rS rSrSU 4S jjrS rSrU =r$ )CohereLayerNorm:   c                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)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       b/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/cohere/modeling_cohere.pyr&   CohereLayerNorm.__init__;   s-    ll5::k#:; #    c                    UR                   nUR                  [        R                  5      nUR	                  SSS9nX-
  R                  S5      R	                  SSS9nX-
  [        R                  " X@R                  -   5      -  nU R                  R                  [        R                  5      U-  nUR                  U5      $ )NT)keepdim   )	dtypetor(   float32meanpowrsqrtr+   r*   )r,   hidden_statesinput_dtyper;   variances        r1   forwardCohereLayerNorm.forwardA   s    #))%((7!!"d!3!(--a055b$5G&-XH]H]=]1^^u}}5E,,r3   )r+   r*   )Ngh㈵>F__name__
__module____qualname____firstlineno__r&   rA   __static_attributes____classcell__r0   s   @r1   r"   r"   :   s    $- -r3   r"   c                   l   ^  \ rS rSrSS\4U 4S jjjr\R                  " 5       \S 5       5       r	Sr
U =r$ )CohereRotaryEmbeddingK   configc                   > [         TU ]  5         [        US5      (       aH  UR                  b;  UR                  R	                  SUR                  R	                  S5      5      U l        OSU l        UR                  U l        UR                  U l        Xl	        [        U R
                     U l        U R                  U R                  U5      u  o0l        U R                  SUSS9  U R                  U l        g )Nrope_scaling	rope_typetypedefaultinv_freqF)
persistent)r%   r&   hasattrrP   getrQ   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrN   r   rope_init_fnattention_scalingregister_bufferrT   original_inv_freq)r,   rN   devicerT   r0   s       r1   r&   CohereRotaryEmbedding.__init__L   s    6>**v/B/B/N#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r3   c                 0   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      nUS S 2S S S 24   R                  5       n[	        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " USSS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR                  UR                   S
9W	R                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r5   r   mpscpuF)device_typeenabledr7   dimr8   )rT   floatexpandshape
isinstancer_   rR   strr(   autocast	transposerepeat_interleavecosr\   sinr9   r8   )
r,   xposition_idsinv_freq_expandedposition_ids_expandedrd   freqsembrq   rr   s
             r1   rA   CohereRotaryEmbedding.forward]   sB    !MM$4-8>>@GGHZHZ[\H]_acde ,QaZ 8 > > @'1!((--'E'E!((--[`J`ahhmmfk^^UC&,,.1F1L1L1NNYYZ[]^_E))%;C'')d444C'')d444C	 D vvAGGv$cff177f&;;; DCs   BF
F)r\   rN   rY   r^   rZ   r[   rQ   N)rD   rE   rF   rG   r   r&   r(   no_gradr   rA   rH   rI   rJ   s   @r1   rL   rL   K   s6    /| / /" ]]_<  <r3   rL   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )	CohereMLPm   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l	        [        UR                     U l        g NFr/   )r%   r&   rN   r-   intermediate_sizer   Linear	gate_projup_proj	down_projr
   
hidden_actact_fnr,   rN   r0   s     r1   r&   CohereMLP.__init__n   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r3   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ rz   )r   r   r   r   )r,   rs   r   s      r1   rA   CohereMLP.forwardx   s6    NN4;;t~~a/@#ADLLQRO#ST	r3   )r   rN   r   r   r-   r   r   rC   rJ   s   @r1   r}   r}   m   s    0 r3   r}   r>   n_repreturnc                     U R                   u  p#pEUS:X  a  U $ U SS2SS2SSS2SS24   R                  X#XU5      n U R                  X#U-  XE5      $ )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)rk   rj   reshape)r>   r   batchnum_key_value_headsslenhead_dims         r1   	repeat_kvr   }   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr3   modulequerykeyvalueattention_maskscalingdropoutc                 @   [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub"  US S 2S S 2S S 2S UR
                  S   24   nX-   n
[        R                  R                  U
S[        R                  S9R                  UR                  5      n
[        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nr7   r	   r5   )rg   r8   )ptrainingr   )r   num_key_value_groupsr(   matmulro   rk   r   
functionalsoftmaxr:   r9   r8   r   r   
contiguous)r   r   r   r   r   r   r   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r1   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#1==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r3   c                 |    U SS S S24   nU SSS S24   n[         R                  " U* U/SS9R                  S5      nU$ )N.r7   r   r5   rf   r   )r(   stackflatten)rs   x1x2rot_xs       r1   rotate_halfr      sL    	
3!8B	
319BKK"b	r*2226ELr3   c                 &   U R                   nU R                  5       n UR                  5       nUR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nUR	                  US9UR	                  US94$ )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.
rh   )r8   ri   	unsqueezer   r9   )	qkrq   rr   rt   unsqueeze_dimr8   q_embedk_embeds	            r1   apply_rotary_pos_embr      s    ( GGE		A		A
--
&C
--
&Cw;q>C/0Gw;q>C/0G::E:"GJJUJ$;;;r3   c                   P  ^  \ rS rSrSrSS\S\\   4U 4S jjjr  SS\	R                  S\\	R                  \	R                  4   S\\	R                     S	\\   S
\\	R                     S\\   S\\	R                  \\	R                     \\\	R                        4   4S jjrSrU =r$ )CohereAttention   z=Multi-headed attention from 'Attention Is All You Need' paperrN   	layer_idxc                 R  > [         TU ]  5         Xl        X l        [	        USUR
                  UR                  -  5      U l        UR                  UR                  -  U l	        U R                  S-  U l
        UR                  U l        SU l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR                  U R                  -  UR
                  UR                  S9U l        UR(                  U l        U R(                  (       a_  [+        UR                  U R                  4UR,                  S9U l        [+        UR                  U R                  4UR,                  S9U l        g g )Nr   g      Tr   r-   r.   )r%   r&   rN   r   getattrr-   num_attention_headsr   r   r   r   attention_dropout	is_causalr   r   attention_biasq_projk_projv_projo_projuse_qk_normr"   layer_norm_epsq_normk_normr,   rN   r   r0   s      r1   r&   CohereAttention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 "--)#77GVMbMbDK *#77GVMbMbDK r3   r>   position_embeddingsr   past_key_valuecache_positionr   r   c                 4   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      n	U R	                  U5      R                  U5      n
U R                  U5      R                  U5      nU R                  (       a"  U R                  U	5      n	U R                  U
5      n
U	R                  SS5      n	U
R                  SS5      n
UR                  SS5      nUu  p[        XX5      u  pUb$  XUS.nUR                  XU R                  U5      u  p[        nU R                  R                  S:w  ad  U R                  R                  S:X  a-  UR!                  SS5      (       a  ["        R%                  S	5        O[&        U R                  R                     nU" U U	U
UU4U R(                  (       d  S
OU R*                  U R,                  S.UD6u  nnUR.                  " / UQSP76 R1                  5       nU R3                  U5      nUU4$ )Nr5   r   r7   )rr   rq   r   eagersdpaoutput_attentionsFz`torch.nn.functional.scaled_dot_product_attention` does not support `output_attentions=True`. Falling back to eager attention. This warning can be removed using the argument `attn_implementation="eager"` when loading the model.        )r   r   )rk   r   r   viewr   r   r   r   r   ro   r   updater   r   rN   _attn_implementationrW   loggerwarning_oncer   r   r   r   r   r   r   )r,   r>   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rq   rr   cache_kwargsattention_interfacer   r   s                     r1   rA   CohereAttention.forward   s    $))#2.88b8$--8{{=166|D[[/44\B
{{=166|D;;|4LZ0J#--a3))!Q/
#--a3&#7RU#[ %#&nUL'5'<'<ZW[WeWegs't$J(?;;++w6{{//69fjjI\^c>d>d##L
 '>dkk>^>^&_#$7	%
  $}}C$2H2HLL	%
 	%
!\ "));;;;FFHkk+.L((r3   )r   rN   r   r   r   r   r   r   r   r   r   r   r   r   rz   )NN)rD   rE   rF   rG   __doc__r   r   intr&   r(   Tensorr   r   
LongTensorr   r   rA   rH   rI   rJ   s   @r1   r   r      s    G|   J +/597)||7) #5<<#=>7) !.	7)
 !7) !!1!127) -.7) 
u||Xell3XeELL>Q5RR	S7) 7)r3   r   c                     ^  \ rS rSrS\S\4U 4S jjr       SS\R                  S\	\R                     S\	\R                     S\	\   S	\	\   S
\	\   S\	\R                     S\	\\R                  \R                  4      S\\   S\\R                   \	\\R                   \R                   4      4   4S jjrSrU =r$ )CohereDecoderLayeri&  rN   r   c                    > [         TU ]  5         UR                  U l        [        XS9U l        [        U5      U l        [        UR                  UR                  S9U l	        g )N)rN   r   r   )
r%   r&   r-   r   	self_attnr}   mlpr"   r   input_layernormr   s      r1   r&   CohereDecoderLayer.__init__'  sP    !--(LV$.F<N<NU[UjUjkr3   r>   r   rt   r   r   	use_cacher   r   r   r   c	                     Un
U R                  U5      nU R                  " SUUUUUUUUS.U	D6u  pU R                  U5      nX-   U-   nU4nU(       a  X4-  nU$ )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   rt   r   r   r   r   r    )r   r   r   )r,   r>   r   rt   r   r   r   r   r   r   residualhidden_states_attentionself_attn_weightshidden_states_mlpoutputss                  r1   rA   CohereDecoderLayer.forward.  s    > !,,]; 6:^^ 
6
')%)/) 3
6
 
6
2 !HH]3 !:=NN "++Gr3   )r-   r   r   r   )NNNFFNN)rD   rE   rF   rG   r   r   r&   r(   r   r   r   r   boolr   r   r   FloatTensorrA   rH   rI   rJ   s   @r1   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: :r3   r   c                   N    \ rS rSr\rSrSrS/rS/r	Sr
SrSrSrSrSrSrS rSrg)	CoherePreTrainedModelik  modelTr   past_key_valuesc                    U R                   R                  n[        U[        R                  5      (       aW  UR
                  R                  R                  SUS9  UR                  b%  UR                  R                  R                  5         g g [        U[        R                  5      (       ad  UR
                  R                  R                  SUS9  UR                  b2  UR
                  R                  UR                     R                  5         g g [        U[        5      (       a&  UR
                  R                  R                  S5        g g )Nr   )r;   stdg      ?)rN   initializer_rangerl   r   r   r*   datanormal_r/   zero_	Embeddingpadding_idxr"   fill_)r,   r   r   s      r1   _init_weights#CoherePreTrainedModel._init_weightsz  s    kk++fbii((MM&&CS&9{{&  &&( '--MM&&CS&9!!-""6#5#56<<> .00MM$$S) 1r3   r   N)rD   rE   rF   rG   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  rH   r   r3   r1   r   r   k  sS    L&*#-.#4"5!N  $!"&*r3   r   c                     ^  \ rS rSrS\4U 4S jjrS rS r\\	         SS\
\R                     S\
\R                     S\
\R                     S	\
\   S
\
\R                     S\
\   S\
\   S\
\   S\
\R                     S\\   S\4S jj5       5       r SS\\R                  S4   S\R                  S\R                  S	\S\4
S jjr\S\R                  S\S\S\R2                  S\R                  S\4S j5       rSrU =r$ )CohereModeli  rN   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )Nr   )rN   F)r%   r&   pad_token_idr  
vocab_sizer   r  r-   embed_tokens
ModuleListrangenum_hidden_layersr   layersr"   r   normrL   
rotary_embgradient_checkpointing	post_initr   s      r1   r&   CohereModel.__init__  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdDcy2Dcd
 $1C1C&J_J_`	/v>&+# 	 es   C?c                     U R                   $ rz   r  r,   s    r1   get_input_embeddings CohereModel.get_input_embeddings  s       r3   c                     Xl         g rz   r%  r,   r   s     r1   set_input_embeddings CohereModel.set_input_embeddings  s    !r3   	input_idsr   rt   r   inputs_embedsr   r   output_hidden_statesr   flash_attn_kwargsr   c
                 J   Ub  UOU R                   R                  nUb  UOU R                   R                  nUb  UOU R                   R                  nUS L US L-  (       a  [	        S5      eU R
                  (       a/  U R                  (       a  U(       a  [        R                  S5        Sn[        U[        S 5      [        45      (       d  [	        S5      eUc  U R                  U5      nU(       a  Uc
  [        5       nU	cD  Ub  UR                  5       OSn[        R                   " XUR"                  S   -   UR$                  S9n	Uc  U	R'                  S5      nU R)                  X%XU5      nUnU R+                  X5      nU(       a  SOS nU(       a  SOS nU R,                  S U R                   R.                    H7  nU(       a  X4-  nU" U4UUUUUU	US	.U
D6nUS   nU(       d  M.  UUS   4-  nM9     U R1                  U5      nU(       a  X4-  n[3        UU(       a  UOS UUS
9$ )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   r_   r   )r   rt   r   r   r   r   r   )last_hidden_stater   r>   
attentions)rN   r   r/  r   
ValueErrorr!  r   r   r   rl   rR   r   r  r   get_seq_lengthr(   arangerk   r_   r   _update_causal_maskr   r  r  r  r   )r,   r-  r   rt   r   r.  r   r   r/  r   r0  past_seen_tokensr   r>   r   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r1   rA   CohereModel.forward  sI    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"\\ ]5H5H5K"KTaThThN )33A6L..>L]
 & #oomJ #7BD0d![[)H4;;+H+HIM#!%55!)
*)."3#-$7
 $
M *!,M  =#3"55' J* 		-0  !11&+/8Od+%	
 	
r3   r   input_tensorc           	         U R                   R                  S:X  a  Ub  US:H  R                  5       (       a  U$ g U R                   R                  S:X  a,  [        U[        R
                  5      (       a  [        U5      nU$ Ub  UR                  5       OSnUb  UR                  OSnU R                   R                  S:X  a5  U(       d.  U(       d'  [        R                  " UUUU R                  S9(       a  g UR                  nUR                  S   n	U(       a  UR                  5       n
O5[        U[        R
                  5      (       a  UR                  S	   OXi-   S-   n
U R                  UU	U
UUUR                  S   S
9nU R                   R                  S:X  aZ  UbW  UR                   R"                  S;   a=  U(       d6  [        R$                  " U5      R&                  n[        R(                  " X5      nU$ )Nflash_attention_2r   flex_attentionr   Fr   )r.  past_key_values_lengthis_trainingr   r5   )sequence_lengthtarget_lengthr8   r   
batch_size)cudaxpunpu)rN   r   anyrl   r(   r   r    r6  is_compileabler   _ignore_causal_mask_sdpar   r8   rk   get_max_cache_shape5_prepare_4d_causal_attention_mask_with_cache_positionr_   rR   finfomin_unmask_unattended)r,   r   r?  r   r   r   r9  using_compilable_cacher8   rE  rF  r   	min_dtypes                r1   r8  CohereModel._update_causal_mask   s    ;;++/BB)~/D.I.I.K.K%%;;++/??.%,,77!<^!L!!
 @O?Z?99;`aCRC^!?!?di ;;++v5>T]n%>>*'7 MM	 ""&,,Q/!+??AM nell;; $$R(%7!;  PP+')#))!, Q 
 KK,,6*%%**.DD%
 E*..I0CCK[Kr3   rE  rF  r8   rG  c                    U b  U R                  5       S:X  a  U nU$ [        R                  " U5      R                  n[        R                  " X4XUR
                  S9nUS:w  a  [        R                  " USS9nU[        R                  " X$R
                  S9UR                  SS5      :  -  nUSSSS2SS24   R                  USSS5      nU b  UR                  5       nU R                  S   n	USS2SS2SS2SU	24   U SS2SSSS24   R                  UR
                  5      -   n
U
S:H  n
USS2SS2SS2SU	24   R                  X5      USS2SS2SS2SU	24'   U$ )	a  
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_valuer8   r_   r   )diagonalr2  r5   r   )rg   r(   rP  rQ  fullr_   triur7  r   rj   clonerk   r9   masked_fill)r   rE  rF  r8   r   rG  r   r   rT  mask_lengthpadding_masks              r1   rO  ACohereModel._prepare_4d_causal_attention_mask_with_cache_positionD  s}   < %.*<*<*>!*C(K* ' E*..I** 0Y\j\q\qK !##jjqA5<<>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 r3   )r  r!  r  r  r  r   r  )	NNNNNNNNN)F)rD   rE   rF   rG   r   r&   r'  r+  r   r   r   r(   r   r   r   r   r   r   r   r   rA   r   r8  staticmethodr   r8   rO  rH   rI   rJ   s   @r1   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r3   r  c                       \ rS rSrSrg)KwargsForCausalLMi|  r   N)rD   rE   rF   rG   rH   r   r3   r1   rc  rc  |  s    3r3   rc  c                     ^  \ rS rSrS/rSS0rSS/S/40rU 4S jrS rS	 r	S
 r
S rS rS r\\           SS\\R$                     S\\R&                     S\\R$                     S\\\\\R.                     4      S\\R.                     S\\R$                     S\\   S\\   S\\   S\\R$                     S\\\R&                  4   S\\   S\4S jj5       5       rSrU =r$ )CohereForCausalLMi  zlm_head.weightlm_headcolwise_repr>   logitsc                 (  > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        UR                  U l	        UR                  U l
        U R                  5         g r   )r%   r&   r  r   r  r   r   r-   rf  logit_scaletie_word_embeddingsr"  r   s     r1   r&   CohereForCausalLM.__init__  sq      (
 ++yy!3!3V5F5FUS!--#)#=#=  	r3   c                 .    U R                   R                  $ rz   r   r  r&  s    r1   r'  &CohereForCausalLM.get_input_embeddings  s    zz&&&r3   c                 $    XR                   l        g rz   rn  r*  s     r1   r+  &CohereForCausalLM.set_input_embeddings  s    "'

r3   c                     U R                   $ rz   rf  r&  s    r1   get_output_embeddings'CohereForCausalLM.get_output_embeddings  s    ||r3   c                     Xl         g rz   rs  )r,   new_embeddingss     r1   set_output_embeddings'CohereForCausalLM.set_output_embeddings  s    %r3   c                     Xl         g rz   r   )r,   decoders     r1   set_decoderCohereForCausalLM.set_decoder  s    
r3   c                     U R                   $ rz   r{  r&  s    r1   get_decoderCohereForCausalLM.get_decoder  s    zzr3   r-  r   rt   r   r.  labelsr   r   r/  r   logits_to_keepr   r   c                    Ub  UOU R                   R                  nU	b  U	OU R                   R                  n	U R                  " SUUUUUUUU	U
S.	UD6nUR                  n[        U[        5      (       a  [        U* S5      OUnU R                  USS2USS24   5      nUU R                  -  nSnUb)  U R                  " SUX`R                   R                  S.UD6n[        UUUR                  UR                  UR                  S9$ )a  
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   rt   r   r.  r   r   r/  r   )rh  r  r  )lossrh  r   r>   r4  r   )rN   r   r/  r   r3  rl   r   slicerf  rj  loss_functionr  r   r   r>   r4  )r,   r-  r   rt   r   r.  r  r   r   r/  r   r  r   r   r>   slice_indicesrh  r  s                     r1   rA   CohereForCausalLM.forward  s(   N 2C1N-TXT_T_TqTq$8$D $++JjJj 	
 ,0:: ,
)%+'/!5),
 ,
  118B>SV8W8W~ot4]kmA}a,?@A$***%%pVF{{OeOepiopD%#33!//))
 	
r3   )rf  rj  r   rk  r  )NNNNNNNNNNr   ) rD   rE   rF   rG   _tied_weights_keys_tp_plan_pp_planr&   r'  r+  rt  rx  r}  r  r   r   r   r(   r   r   r   r   r   r   r   r   r   rc  r   rA   rH   rI   rJ   s   @r1   re  re    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
r3   re  )re  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_loggerrD   r   Moduler"   rL   r}   r   r   r   ri   r   r   r   r   r   r   r  rc  re  __all__r   r3   r1   <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r3   