
    3j`X                        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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\RX                  S\-S\RX                  4S jr. S3S\RR                  S\RX                  S\RX                  S\RX                  S\RX                  S-  S \/S!\/S"\\   4S# jjr0S$ r1S4S% jr2 " S& S'\RR                  5      r3 " S( S)\RR                  5      r4 " S* S+\5      r5\  " S, S-\5      5       r6\  " S. S/\65      5       r7\  " S0 S1\6\5      5       r8/ S2Qr9g)5    )Callable)OptionalN   )ACT2FN)CacheDynamicCache)GenerationMixin)create_causal_mask!create_sliding_window_causal_mask)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs   )Cohere2Configc                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\	   SS\S-  S\
S   S\S-  S	\S
\4   4S jj5       r\R                  " 5       \S 5       5       rSrU =r$ )Cohere2RotaryEmbedding*   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defaultr   F)
persistentoriginal_inv_freq)super__init__max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr    rope_parametersr"   compute_default_rope_parametersr   attention_scalingregister_bufferclone)selfr    devicerope_init_fnr   	__class__s        f/home/wildlama/miniconda3/lib/python3.13/site-packages/transformers/models/cohere2/modeling_cohere2.pyr'   Cohere2RotaryEmbedding.__init__-   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuU    r1   ztorch.deviceseq_lenreturnztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	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      dtype)r1   r>   )	r+   getattrhidden_sizenum_attention_headstorcharangeint64tofloat)r    r1   r7   basedimattention_factorr   s          r4   r,   6Cohere2RotaryEmbedding.compute_default_rope_parameters=   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r6   c                    U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      nUS S 2S S S 24   R                  5       n[	        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " USSS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR                  UR                   S
9W	R                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r   mpscpuF)device_typeenabledr<   rH   r=   )r   rF   expandshape
isinstancer1   typestrr   	transposerB   repeat_interleavecosr-   sinrE   r>   )
r0   xposition_idsinv_freq_expandedposition_ids_expandedrO   freqsembrY   rZ   s
             r4   forwardCohere2RotaryEmbedding.forward[   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
)r-   r    r)   r*   r"   N)NNN)__name__
__module____qualname____firstlineno__rB   Tensor__annotations__r   r'   staticmethodr   inttuplerF   r,   no_gradr   ra   __static_attributes____classcell__r3   s   @r4   r   r   *   s    llV} V V  '++/"*$*(* t* 
~u$	%	* *: ]]_<  <r6   r   c                   2   ^  \ rS rSrSU 4S jjrS rSrU =r$ )Cohere2LayerNormk   c                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)zcThe hidden size can be a tuple or an int. The tuple is used for QKNorm to normalize across head_dimN)r&   r'   nn	ParameterrB   onesweightvariance_epsilon)r0   r@   epsbiasr3   s       r4   r'   Cohere2LayerNorm.__init__l   s-    ll5::k#:; #r6   c                    UR                   nUR                  [        R                  5      nUR	                  SSS9nX-
  R                  S5      R	                  SSS9nX-
  [        R                  " X@R                  -   5      -  nU R                  R                  [        R                  5      U-  nUR                  U5      $ )NrL   T)keepdimr<   )	r>   rE   rB   float32meanpowrsqrtry   rx   )r0   hidden_statesinput_dtyper   variances        r4   ra   Cohere2LayerNorm.forwardr   s    #))%((7!!"d!3!(--a055b$5G&-XH]H]=]1^^u}}5E,,r6   )ry   rx   )Ngh㈵>Frd   re   rf   rg   r'   ra   rn   ro   rp   s   @r4   rr   rr   k   s    $- -r6   rr   r   n_repr8   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)rS   rR   reshape)r   r   batchnum_key_value_headsslenr;   s         r4   	repeat_kvr   |   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr6   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$ )Nr<   r   rL   )rH   r>   )ptrainingr   )r   num_key_value_groupsrB   matmulrW   ru   
functionalsoftmaxr   rE   r>   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r4   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r6   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$ )N.r<   r   rL   rQ   )rB   stackflatten)r[   x1x2rot_xs       r4   rotate_halfr      sL    	
3!8B	
319BKK"b	r*2226ELr6   c                 &   U R                   nU R                  5       n UR                  5       nUR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nUR	                  US9UR	                  US94$ )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.
r=   )r>   rF   	unsqueezer   rE   )qkrY   rZ   unsqueeze_dimr>   q_embedk_embeds           r4   apply_rotary_pos_embr      s    $ GGE		A		A
--
&C
--
&Cw;q>C/0Gw;q>C/0G::E:"GJJUJ$;;;r6   c                   0  ^  \ 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-  \
\R                     S-  4   4S jjrSrU =r$ )Cohere2Attention   z=Multi-headed attention from 'Attention Is All You Need' paperNr    	layer_idxc                   > [         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        UR                  U   S:X  a  UR                  O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        g )Nr;   g      Tsliding_attentionr{   )r&   r'   r    r   r?   r@   rA   r;   r   r   r   attention_dropout	is_causallayer_typessliding_windowru   Linearattention_biasq_projk_projv_projo_projr0   r    r   r3   s      r4   r'   Cohere2Attention.__init__   sm   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!97=7I7I)7TXk7kf33quii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r6   r   position_embeddingsr   past_key_valuesr   r8   c                 8   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
Uu  pU R                  b  [        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [        5      nU" U UU	U
U4U R                   (       d  SOU R"                  U R$                  U R                  S.UD6u  pUR&                  " / UQSP76 R)                  5       nU R+                  U5      nX4$ )NrL   r   r<           )r   r   r   )rS   r;   r   viewrW   r   r   r   r   updater   r   get_interfacer    _attn_implementationr   r   r   r   r   r   r   )r0   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rY   rZ   attention_interfacer   r   s                   r4   ra   Cohere2Attention.forward   s    $))#2.88b8$--8{{=166|DNNqRST[[/44\BLLQPQR
{{=166|DNNqRST&*';LVY'_$L&'6'='=jX\XfXf'g$J(?(M(MKK,,.E)
 %8
%
  $}}C$2H2HLL..
%
 
%
! "));;;;FFHkk+.((r6   )r   r    r;   r   r   r   r   r   r   r   r   r   rc   )rd   re   rf   rg   __doc__r   rk   r'   rB   rh   rl   r   r   r   ra   rn   ro   rp   s   @r4   r   r      s    G
} 
t 
 
: )-()||() #5<<#=>() t+	()
 () +,() 
u||U\\D0%2E2LL	M() ()r6   r   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )
Cohere2MLPi  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 NFr   )r&   r'   r    r@   intermediate_sizeru   r   	gate_projup_proj	down_projr   
hidden_actact_fnr0   r    r3   s     r4   r'   Cohere2MLP.__init__  s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r6   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ rc   )r   r   r   r   )r0   r[   r   s      r4   ra   Cohere2MLP.forward  s6    NN4;;t~~a/@#ADLLQRO#ST	r6   )r   r    r   r   r@   r   r   r   rp   s   @r4   r   r     s    0 r6   r   c                   4  ^  \ rS rSrS\S\4U 4S jjr    SS\R                  S\	\R                  \R                  4   S-  S\R                  S-  S	\
S-  S
\S-  S\\   S\	\R                  \	\R                  \R                  4   S-  4   4S jjrSrU =r$ )Cohere2DecoderLayeri  r    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)r    r   r@   rz   )
r&   r'   r@   r   	self_attnr   mlprr   layer_norm_epsinput_layernormr   s      r4   r'   Cohere2DecoderLayer.__init__  sP    !--)Mf%/V=O=OV\VkVklr6   Nr   r   r   r   	use_cacher   r8   c           	          UnU R                  U5      nU R                  " SUUUUUS.UD6u  pU R                  U5      n
Xx-   U
-   nU$ )a<  
Args:
    hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
    attention_mask (`torch.FloatTensor`, *optional*):
        attention mask of size `(batch_size, sequence_length)` if flash attention is used or `(batch_size, 1,
        query_sequence_length, key_sequence_length)` if default attention is used.
    past_key_values (`Cache`, *optional*): cached past key and value projection states
    output_attentions (`bool`, *optional*):
        Whether or not to return the attentions tensors of all attention layers. See `attentions` under
        returned tensors for more detail.
    use_cache (`bool`, *optional*):
        If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
        (see `past_key_values`).
    position_embeddings (`tuple[torch.FloatTensor, torch.FloatTensor]`, *optional*):
        Tuple containing the cosine and sine positional embeddings of shape `(batch_size, seq_len, head_dim)`,
        with `head_dim` being the embedding dimension of each attention head.
)r   r   r   r   r    )r   r   r   )r0   r   r   r   r   r   r   residualhidden_states_attention_hidden_states_mlps              r4   ra   Cohere2DecoderLayer.forward#  sn    4 !,,];%)^^ &
' 3)+&
 &
" !HH]3 :=NNr6   )r@   r   r   r   )NNNF)rd   re   rf   rg   r   rk   r'   rB   rh   rl   r   boolr   r   FloatTensorra   rn   ro   rp   s   @r4   r   r     s    m} m m IM.2(,!&'||' #5<<#=>E' t+	'
 ' $;' +,' 
u  %(9(95;L;L(L"MPT"TT	U' 'r6   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	)
Cohere2PreTrainedModeliM  r    modelTr   r   )r   
attentionsr   N)rd   re   rf   rg   r   ri   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_outputsrn   r   r6   r4   r   r   M  sQ    &*#./#4"5N!"&,&r6   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$ )Cohere2Modeli`  r    c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        U5      U l        SU l        U R)                  5         g s  snf )Nr   F)r&   r'   pad_token_idpadding_idx
vocab_sizeru   	Embeddingr@   embed_tokens
ModuleListrangenum_hidden_layersr   layersrr   r   normr   
rotary_embgradient_checkpointing	post_initr   s      r4   r'   Cohere2Model.__init__b  s     !.. ++LL):):F<N<NPTP`P`ammEJ6KcKcEdeEd	 3Ede
 %&2D2D6K`K`a	08&+# 	 fs   DN	input_idsr   r\   r   inputs_embedsr   r   r8   c           
         US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcU  Ub  UR	                  5       OSn[
        R                  " UR                  S   UR                  S9U-   nUR                  S5      n[        U=n	[        5      (       d)  U R                  UUUUS.n
[        S
0 U
D6[        S
0 U
D6S.n	UnU R                  X5      n[        U R                   5       H-  u  pU" U4XR                  R"                  U      UUUUS.UD6nM/     U R%                  U5      n['        UUS	9$ )Nz:You must specify exactly one of input_ids or inputs_embeds)r    r   r   )r1   )r    r  r   r   r\   )full_attentionr   )r   r   r   r   r\   )last_hidden_stater   r   )
ValueErrorr  r   r    get_seq_lengthrB   rC   rS   r1   r   rT   dictr
   r   r  	enumerater  r   r  r   )r0   r  r   r\   r   r  r   r   past_seen_tokenscausal_mask_mappingmask_kwargsr   r   idecoder_layers                  r4   ra   Cohere2Model.forwardq  s{    -t";<YZZ  --i8M0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L?-FF++!."0#2 ,K #5"C{"C%F%U%U#
 &"oomJ )$++ 6A)2;;3J3J13MN$7 /#) M !7 		-0&++
 	
r6   )r  r  r  r  r  r  r	  )NNNNNN)rd   re   rf   rg   r   r'   r   r   r   rB   
LongTensorrh   r   r   r   r   r   r   ra   rn   ro   rp   s   @r4   r  r  `  s    }    .2.204(,26!%7
##d*7
 t+7
 &&-	7

 7
 ((4/7
 $;7
 +,7
 
!7
    7
r6   r  c                   P  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )Cohere2ForCausalLMi  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	  ru   r   r@   r'  logit_scaletie_word_embeddingsr  r   s     r4   r'   Cohere2ForCausalLM.__init__  sq     !&)
 ++yy!3!3V5F5FUS!--#)#=#=  	r6   Nr  r   r\   r   r  labelsr   logits_to_keepr   r8   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$ )ay  
Example:

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

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

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

>> # Generate
>> generate_ids = model.generate(inputs.input_ids, max_length=30)
>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
"Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
```)r  r   r\   r   r  r   N)r)  r.  r	  )lossr)  r   r   r   r   )r   r  rT   rk   slicer'  r+  loss_functionr    r	  r   r   r   r   )r0   r  r   r\   r   r  r.  r   r/  r   outputsr   slice_indicesr)  r1  s                  r4   ra   Cohere2ForCausalLM.forward  s    > ,0:: ,
)%+',
 ,
  118B>SV8W8W~ot4]kmA}a,?@A***%%pVt{{OeOepiopD%#33!//))
 	
r6   )r'  r+  r   r,  r	  )NNNNNNNr   )rd   re   rf   rg   _tied_weights_keys_tp_plan_pp_planr'   r   r   rB   r$  rh   r   r   r   rk   r   r   r   ra   rn   ro   rp   s   @r4   r&  r&    s   *,GH23H_-z:;H	  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
r6   r&  )r&  r  r   )r   )r   ):collections.abcr   typingr   rB   torch.nnru   activationsr   cache_utilsr   r   
generationr	   masking_utilsr
   r   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.output_capturingr   configuration_cohere2r   Moduler   rr   rh   rk   r   rF   r   r   r   r   r   r   r   r  r&  __all__r   r6   r4   <module>rL     s  * %    ! . ) R 9 O K F & I I G 5 0><RYY ><B-ryy -"	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2<8C)ryy C)L  /4 /d _  $ J
) J
 J
Z H
/ H
 H
V Kr6   