
    3jZ                     
   S SK Jr  S SK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!  SSK"J#r#J$r$  SSK%J&r&  SSK'J(r(   " S S\RR                  5      r* " S S\RR                  5      r+ " S S\RR                  5      r,S\RZ                  S\.S\RZ                  4S jr/ S5S\RR                  S \RZ                  S!\RZ                  S"\RZ                  S#\RZ                  S-  S$\0S%\0S&\\   4S' jjr1S( r2S6S) jr3 " S* S+\RR                  5      r4 " S, S-\5      r5\  " S. S/\5      5       r6\  " S0 S1\65      5       r7\  " S2 S3\6\5      5       r8/ S4Qr9g)7    )Callable)OptionalN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)create_causal_mask)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs   )CohereConfigc                   2   ^  \ rS rSrSU 4S jjrS rSrU =r$ )CohereLayerNorm3   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       d/home/wildlama/miniconda3/lib/python3.13/site-packages/transformers/models/cohere/modeling_cohere.pyr"   CohereLayerNorm.__init__4   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_dtyper7   variances        r-   forwardCohereLayerNorm.forward:   s    #))%((7!!"d!3!(--a055b$5G&-XH]H]=]1^^u}}5E,,r/   )r'   r&   )Ngh㈵>F__name__
__module____qualname____firstlineno__r"   r=   __static_attributes____classcell__r,   s   @r-   r   r   3   s    $- -r/   r   c                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\	   SS\S-  S\
S   S\S-  S	\S
\4   4S jj5       r\R                  " 5       \S 5       5       rSrU =r$ )CohereRotaryEmbeddingD   inv_freqNconfigc                   > [         TU ]  5         UR                  U l        UR                  U l        Xl        U R
                  R                  S   U l        U R                  nU R                  S:w  a  [        U R                     nU" U R
                  U5      u  o@l
        U R                  SUSS9  U R                  SUR                  5       SS9  g )N	rope_typedefaultrJ   F)
persistentoriginal_inv_freq)r!   r"   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrK   rope_parametersrM   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r(   rK   devicerope_init_fnrJ   r,   s        r-   r"   CohereRotaryEmbedding.__init__G   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr/   rY   ztorch.deviceseq_lenreturnztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	aH  
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   r3   r4   )rY   r4   )	rT   getattrr)   num_attention_headsr$   arangeint64r5   float)rK   rY   r\   basedimattention_factorrJ   s          r-   rU   5CohereRotaryEmbedding.compute_default_rope_parametersW   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r/   c                    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[        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$ ! , (       d  f       N@= f)Nr   r1   r   mpscpuF)device_typeenabledr3   rh   ra   )rJ   rf   expandshape
isinstancerY   typestrr   	transposer$   repeat_interleavecosrV   sinr5   r4   )
r(   xposition_idsinv_freq_expandedposition_ids_expandedrn   freqsembrx   ry   s
             r-   r=   CohereRotaryEmbedding.forwardu   s>    !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E<<
F
)rV   rK   rR   rS   rM   N)NNN)r@   rA   rB   rC   r$   Tensor__annotations__r   r"   staticmethodr   inttuplerf   rU   no_gradr   r=   rD   rE   rF   s   @r-   rH   rH   D   s    llV| V V  &*+/"*t#*(* t* 
~u$	%	* *: ]]_<  <r/   rH   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )	CohereMLP   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l	        [        UR                     U l        g NFr+   )r!   r"   rK   r)   intermediate_sizer   Linear	gate_projup_proj	down_projr   
hidden_actact_fnr(   rK   r,   s     r-   r"   CohereMLP.__init__   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r/   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r   )r   r   r   r   )r(   rz   r   s      r-   r=   CohereMLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r/   )r   rK   r   r   r)   r   r   r?   rF   s   @r-   r   r      s    0 r/   r   r:   n_repr]   c                     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)rr   rq   reshape)r:   r   batchnum_key_value_headsslenr`   s         r-   	repeat_kvr      s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr/   modulequerykeyvalueattention_maskscalingdropoutkwargsc                    [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub  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$ )Nr3   r   r1   )rh   r4   )ptrainingr   )r   num_key_value_groupsr$   matmulrv   r   
functionalsoftmaxr6   r5   r4   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r-   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r/   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$ )N.r3   r   r1   rp   )r$   stackflatten)rz   x1x2rot_xs       r-   rotate_halfr      sL    	
3!8B	
319BKK"b	r*2226ELr/   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$ )aI  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.
ra   )r4   rf   	unsqueezer   r5   )qkrx   ry   unsqueeze_dimr4   q_embedk_embeds           r-   apply_rotary_pos_embr      s    $ GGE		A		A
--
&C
--
&Cw;q>C/0Gw;q>C/0G::E:"GJJUJ$;;;r/   c                     ^  \ rS rSrSrSS\S\S-  4U 4S jjjr SS\R                  S\
\R                  \R                  4   S	\R                  S-  S
\S-  S\\   S\
\R                  \R                  S-  4   4S jjrSrU =r$ )CohereAttention   z=Multi-headed attention from 'Attention Is All You Need' paperNrK   	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"   rK   r   rb   r)   rc   r`   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(   rK   r   r,   s      r-   r"   CohereAttention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 "--)#77GVMbMbDK *#77GVMbMbDK r/   r:   position_embeddingsr   past_key_valuesr   r]   c                 z   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      nU R	                  U5      R                  U5      n	U R                  U5      R                  U5      n
U R                  (       a"  U R                  U5      nU R                  U	5      n	UR                  SS5      nU	R                  SS5      n	U
R                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                   ["        5      nU" U UU	U
U4U R$                  (       d  SOU R&                  U R(                  S.UD6u  pUR*                  " / UQSP76 R-                  5       nU R/                  U5      nX4$ )Nr1   r   r3           )r   r   )rr   r`   r   viewr   r   r   r   r   rv   r   updater   r   get_interfacerK   _attn_implementationr   r   r   r   r   r   r   )r(   r:   r   r   r   r   input_shapehidden_shapequery_statesr   r   rx   ry   attention_interfacer   r   s                   r-   r=   CohereAttention.forward  s    $))#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#[ &'6'='=jX\XfXf'g$J(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
! "));;;;FFHkk+.((r/   )r   rK   r`   r   r   r   r   r   r   r   r   r   r   r   r   )r@   rA   rB   rC   __doc__r   r   r"   r$   r   r   r   r   r   r=   rD   rE   rF   s   @r-   r   r      s    G| d
  J )-.)||.) #5<<#=>.) t+	.)
 .) -..) 
u||U\\D00	1.) .)r/   r   c                   T  ^  \ rS rSrS\S\4U 4S jjr     SS\R                  S\R                  S-  S\R                  S-  S	\
S-  S
\S-  S\\R                  \R                  4   S-  S\\   S\\R                  \\R                  \R                  4   S-  4   4S jjrSrU =r$ )CohereDecoderLayeri2  rK   r   c                    > [         TU ]  5         UR                  U l        [        XS9U l        [        U5      U l        [        UR                  UR                  S9U l	        g )N)rK   r   r   )
r!   r"   r)   r   	self_attnr   mlpr   r   input_layernormr   s      r-   r"   CohereDecoderLayer.__init__3  sP    !--(LV$.F<N<NU[UjUjkr/   Nr:   r   r{   r   	use_cacher   r   r]   c           
          UnU R                  U5      nU R                  " SUUUUUUS.UD6u  pU R                  U5      nX-   U-   nU$ )a<  
Args:
    hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
    attention_mask (`torch.FloatTensor`, *optional*):
        attention mask of size `(batch_size, sequence_length)` if flash attention is used or `(batch_size, 1,
        query_sequence_length, key_sequence_length)` if default attention is used.
    past_key_values (`Cache`, *optional*): cached past key and value projection states
    output_attentions (`bool`, *optional*):
        Whether or not to return the attentions tensors of all attention layers. See `attentions` under
        returned tensors for more detail.
    use_cache (`bool`, *optional*):
        If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
        (see `past_key_values`).
    position_embeddings (`tuple[torch.FloatTensor, torch.FloatTensor]`, *optional*):
        Tuple containing the cosine and sine positional embeddings of shape `(batch_size, seq_len, head_dim)`,
        with `head_dim` being the embedding dimension of each attention head.
)r:   r   r{   r   r   r    )r   r   r   )r(   r:   r   r{   r   r   r   r   residualhidden_states_attention_hidden_states_mlps               r-   r=   CohereDecoderLayer.forward:  sq    6 !,,];%)^^ &
')%+ 3&
 &
" !HH]3 :=NNr/   )r)   r   r   r   )NNNFN)r@   rA   rB   rC   r   r   r"   r$   r   
LongTensorr   boolr   r   r   FloatTensorr=   rD   rE   rF   s   @r-   r   r   2  s    l| l l /304(,!&HL*||* t+* &&-	*
 * $;* #5<<#=>E* -.* 
u  %(9(95;L;L(L"MPT"TT	U* *r/   r   c                   R    \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rSrg	)
CoherePreTrainedModelig  rK   modelTr   r   )r:   
attentionsr   N)r@   rA   rB   rC   r   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsrD   r   r/   r-   r   r   g  sQ    &*#-.#4"5N!"&+%r/   r   c                     ^  \ rS rSrS\4U 4S jjr\\\      SS\	R                  S-  S\	R                  S-  S\	R                  S-  S\S-  S	\	R                  S-  S
\S-  S\\   S\4S jj5       5       5       rSrU =r$ )CohereModeliz  rK   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   rK   F)r!   r"   pad_token_idpadding_idx
vocab_sizer   	Embeddingr)   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normrH   
rotary_embgradient_checkpointing	post_initr   s      r-   r"   CohereModel.__init__|  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdDcy2Dcd
 $1C1C&J_J_`	/v>&+# 	 es   C?N	input_idsr   r{   r   inputs_embedsr   r   r]   c           
      >   US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcU  Ub  UR	                  5       OSn[
        R                  " UR                  S   UR                  S9U-   nUR                  S5      n[        U R                  UUUUS9n	Un
U R                  XS9nU R                  S U R                  R                    H  nU" U
4U	UUUUS.UD6n
M     U R                  U
5      n
[        U
US	9$ )
Nz:You must specify exactly one of input_ids or inputs_embedsr	  r   r   )rY   )rK   r  r   r   r{   )r{   )r   r   r{   r   r   )last_hidden_stater   )
ValueErrorr  r	   rK   get_seq_lengthr$   rd   rr   rY   r   r   r  r  r  r  r   )r(   r  r   r{   r   r  r   r   past_seen_tokenscausal_maskr:   r   decoder_layers                r-   r=   CohereModel.forward  sF    -t";<YZZ *.*;*;I*FM0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L(;;')+%
 &"oomoW![[)H4;;+H+HIM)*$7) /# M J 		-0&++
 	
r/   )r  r  r  r  r  r  r  )NNNNNN)r@   rA   rB   rC   r   r"   r   r   r   r$   r   r   r   r   r   r   r   r   r=   rD   rE   rF   s   @r-   r  r  z  s    |     .2.204(,26!%2
##d*2
 t+2
 &&-	2

 2
 ((4/2
 $;2
 +,2
 
!2
    2
r/   r  c                   P  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )CohereForCausalLMi  zlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr:   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)   r$  logit_scaletie_word_embeddingsr  r   s     r-   r"   CohereForCausalLM.__init__  sq      (
 ++yy!3!3V5F5FUS!--#)#=#=  	r/   Nr  r   r{   r   r  labelsr   logits_to_keepr   r]   c	           
         U R                   " SUUUUUUS.U	D6n
U
R                  n[        U[        5      (       a  [	        U* S5      OUnU R                  USS2USS24   5      nXR                  -  nSnUb)  U R                  " SXU R                  R                  S.U	D6n[        UUU
R                  U
R                  U
R                  S9$ )au  
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."
```)r  r   r{   r   r  r   N)r&  r+  r  )lossr&  r   r:   r   r   )r   r  rs   r   slicer$  r(  loss_functionrK   r  r   r   r:   r   )r(   r  r   r{   r   r  r+  r   r,  r   outputsr:   slice_indicesr&  r.  s                  r-   r=   CohereForCausalLM.forward  s    > ,0:: ,
)%+',
 ,
  118B>SV8W8W~ot4]kmA}a,?@A***%%pVt{{OeOepiopD%#33!//))
 	
r/   )r$  r(  r   r)  r  )NNNNNNNr   )r@   rA   rB   rC   _tied_weights_keys_tp_plan_pp_planr"   r   r   r$   r   r   r   r   r   r   r   r   r   r=   rD   rE   rF   s   @r-   r#  r#    s   *,GH23H_-z:;H	  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
r/   r#  )r#  r  r   )r   )r   ):collections.abcr   typingr   r$   r   activationsr   cache_utilsr   r	   
generationr
   masking_utilsr   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.output_capturingr   configuration_coherer   Moduler   rH   r   r   r   r   rf   r   r   r   r   r   r   r  r#  __all__r   r/   r-   <module>rI     s  : %    ! . ) / B 9 O K F & I I G 5 .-bii -"><BII ><B		  	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2<8Q)bii Q)h23 2j O  $ F
' F
 F
R H
- H
 H
V Hr/   