§
    9²¸jŽY  ã                   óÞ  — d dl mZ d dlZd dlmZ ddlmZ ddlmZmZ ddl	m
Z
 ddlmZ 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 ddl m!Z! ddl"m#Z#m$Z$ ddl%m&Z& ddl'm(Z(  G d„ dej)        ¦  «        Z* G d„ dej)        ¦  «        Z+ G d„ dej)        ¦  «        Z,dej-        de.dej-        fd„Z/	 d6d ej)        d!ej-        d"ej-        d#ej-        d$ej-        dz  d%e0d&e0d'ee         fd(„Z1d)„ Z2d7d*„Z3 G d+„ d,ej)        ¦  «        Z4 G d-„ d.e¦  «        Z5e G d/„ d0e¦  «        ¦   «         Z6e G d1„ d2e6¦  «        ¦   «         Z7e G d3„ d4e6e
¦  «        ¦   «         Z8g d5¢Z9dS )8é    )ÚCallableN)Únné   )ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úcreate_causal_mask)ÚFlashAttentionKwargs)ÚGradientCheckpointingLayer)ÚBaseModelOutputWithPastÚCausalLMOutputWithPast)ÚROPE_INIT_FUNCTIONSÚdynamic_rope_update)ÚALL_ATTENTION_FUNCTIONSÚPreTrainedModel)ÚUnpack)ÚTransformersKwargsÚauto_docstringÚcan_return_tuple)Údeprecate_kwarg)Úmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputsé   )ÚCohereConfigc                   ó&   ‡ — e Zd Zdˆ fd„	Zd„ Zˆ xZS )ÚCohereLayerNormNçñhãˆµøä>Fc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )zcThe hidden size can be a tuple or an int. The tuple is used for QKNorm to normalize across head_dimN)ÚsuperÚ__init__r   Ú	ParameterÚtorchÚonesÚweightÚvariance_epsilon)ÚselfÚhidden_sizeÚepsÚbiasÚ	__class__s       €úz/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/cohere/modeling_cohere.pyr"   zCohereLayerNorm.__init__4   sB   ø€ å‰Œ×ÒÑÔÐÝ”l¥5¤:¨kÑ#:Ô#:Ñ;Ô;ˆŒØ #ˆÔÐÐó    c                 ó’  — |j         }|                     t          j        ¦  «        }|                     dd¬¦  «        }||z
                       d¦  «                             dd¬¦  «        }||z
  t          j        || j        z   ¦  «        z  }| j                             t          j        ¦  «        |z  }|                     |¦  «        S )NéÿÿÿÿT)Úkeepdimé   )	ÚdtypeÚtor$   Úfloat32ÚmeanÚpowÚrsqrtr'   r&   )r(   Úhidden_statesÚinput_dtyper6   Úvariances        r-   ÚforwardzCohereLayerNorm.forward:   s±   € Ø#Ô)ˆØ%×(Ò(­¬Ñ7Ô7ˆØ×!Ò! "¨dÐ!Ñ3Ô3ˆØ! DÑ(×-Ò-¨aÑ0Ô0×5Ò5°bÀ$Ð5ÑGÔGˆØ&¨Ñ-µ´¸XÈÔH]Ñ=]Ñ1^Ô1^Ñ^ˆØœŸš¥u¤}Ñ5Ô5¸ÑEˆØ×Ò Ñ,Ô,Ð,r.   )Nr   F©Ú__name__Ú
__module__Ú__qualname__r"   r<   Ú__classcell__©r,   s   @r-   r   r   3   sL   ø€ € € € € ð$ð $ð $ð $ð $ð $ð-ð -ð -ð -ð -ð -ð -r.   r   c            	       óî   ‡ — e Zd Z edd¬¦  «        d
defˆ fd„¦   «         Ze edd¬¦  «        d
dedeej	        e
f         fd„¦   «         ¦   «         Z ej        ¦   «         ed	„ ¦   «         ¦   «         Zˆ xZS )ÚCohereRotaryEmbeddingÚdevicez5.18)ÚversionNÚconfigc                 ó¾  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        | j        j        d         | _        | j        }| j        dk    rt          | j                 } || j        |¦  «        \  }| _
        t          j        |d¬¦  «        | _        t          j        |                     ¦   «         d¬¦  «        | _        d S )NÚ	rope_typeÚdefaultF)Ú
persistent)r!   r"   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrG   Úrope_parametersrI   Úcompute_default_rope_parametersr   Úattention_scalingr   ÚBufferÚinv_freqÚcloneÚoriginal_inv_freq)r(   rG   rE   Úrope_init_fnrS   r,   s        €r-   r"   zCohereRotaryEmbedding.__init__E   sÀ   ø€ å‰Œ×ÒÑÔÐØ"(Ô"@ˆÔØ$*Ô$BˆÔ!àˆŒàœÔ4°[ÔAˆŒØ!%Ô!EˆØŒ>˜YÒ&Ð&Ý.¨t¬~Ô>ˆLØ+7¨<¸¼ÀVÑ+LÔ+LÑ(ˆ�$Ô(åœ	 (°uÐ=Ñ=Ô=ˆŒÝ!#¤¨8¯>ª>Ñ+;Ô+;ÈÐ!NÑ!NÔ!NˆÔÐÐr.   Úreturnc                 óä   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «        |z  z  z  }|                     |¦  «        |fS )a¾  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
        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).
        Ú
rope_thetaÚhead_dimNg      ð?r   r2   ©r3   )rO   Úgetattrr)   Únum_attention_headsr$   ÚarangeÚfloatr4   )rG   rE   ÚkwargsÚbaseÚdimÚattention_factorrS   s          r-   rP   z5CohereRotaryEmbedding.compute_default_rope_parametersV   sz   € ð Ô% lÔ3ˆÝ�f˜j¨$Ñ/Ô/Ðc°6Ô3EÈÔIcÑ3cˆàÐà˜$¥5¤<°°3¸ÅÄÐ#MÑ#MÔ#MÐPSÑ#SÑTÑUˆØ�{Š{˜6Ñ"Ô"Ð$4Ð4Ð4r.   c                 ó  — | j         d d d …d f                              ¦   «                              |j        d         dd¦  «        }|d d …d d d …f                              ¦   «         }t	          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  |                     ¦   «         |                     ¦   «         z   	                    dd¦  «        }t          j        |dd¬	¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬
¦  «        |	                     |j        ¬
¦  «        fS )Nr   r0   r   ÚmpsÚcpuF)Údevice_typeÚenabledr2   ©rb   r[   )rS   r_   ÚexpandÚshapeÚ
isinstancerE   ÚtypeÚstrr   Ú	transposer$   Úrepeat_interleaveÚcosrQ   Úsinr4   r3   )
r(   ÚxÚposition_idsÚinv_freq_expandedÚposition_ids_expandedrg   ÚfreqsÚembrq   rr   s
             r-   r<   zCohereRotaryEmbedding.forwardj   s¤  € ð !œM¨$°°°°4¨-Ô8×>Ò>Ñ@Ô@×GÒGÈÔHZÐ[\ÔH]Ð_aÐcdÑeÔeÐØ ,¨Q¨Q¨Q°°a°a°a¨ZÔ 8× >Ò >Ñ @Ô @Ðå'1°!´(´-ÅÑ'EÔ'EÐkÈ!Ì(Ì-Ð[`ÒJ`ÐJ`�a”h”m�mÐfkˆÝ¨¸UÐCÑCÔCð 	5ð 	5Ø&×,Ò,Ñ.Ô.Ð1F×1LÒ1LÑ1NÔ1NÑN×YÒYÐZ[Ð]^Ñ_Ô_ˆEÝÔ)¨%°¸Ð;Ñ;Ô;ˆCØ—'’'‘)”)˜dÔ4Ñ4ˆCØ—'’'‘)”)˜dÔ4Ñ4ˆCð		5ð 	5ð 	5ñ 	5ô 	5ð 	5ð 	5ð 	5ð 	5ð 	5ð 	5øøøð 	5ð 	5ð 	5ð 	5ð �vŠv˜AœGˆvÑ$Ô$ c§f¢f°1´7 fÑ&;Ô&;Ð;Ð;s   Â4BEÅEÅE©N)r>   r?   r@   r   r   r"   ÚstaticmethodÚtupler$   ÚTensorr_   rP   Úno_gradr   r<   rA   rB   s   @r-   rD   rD   D   sö   ø€ € € € € Ø€_�X vÐ.Ñ.Ô.ðOð O˜|ð Oð Oð Oð Oð Oñ /Ô.ðOð  Ø€_�X vÐ.Ñ.Ô.ð5ð 5°ð 5ÐX]Ð^cÔ^jÐlqÐ^qÔXrð 5ð 5ð 5ñ /Ô.ñ „\ð5ð$ €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r.   rD   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )Ú	CohereMLPc                 ó˜  •— t          ¦   «                              ¦   «          || _        |j        | _        |j        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _	        t          |j                 | _        d S ©NF©r+   )r!   r"   rG   r)   Úintermediate_sizer   ÚLinearÚ	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©r(   rG   r,   s     €r-   r"   zCohereMLP.__init__{   s¦   ø€ Ý‰Œ×ÒÑÔÐØˆŒØ!Ô-ˆÔØ!'Ô!9ˆÔÝœ 4Ô#3°TÔ5KÐRWÐXÑXÔXˆŒÝ”y Ô!1°4Ô3IÐPUÐVÑVÔVˆŒÝœ 4Ô#9¸4Ô;KÐRWÐXÑXÔXˆŒÝ˜VÔ.Ô/ˆŒˆˆr.   c                 ó¨   — |                       |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        }|S ry   )r‡   r‰   r…   r†   )r(   rs   r‡   s      r-   r<   zCohereMLP.forward…   sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr.   r=   rB   s   @r-   r   r   z   sG   ø€ € € € € ð0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð r.   r   r9   Ún_reprW   c                 ó¸   — | j         \  }}}}|dk    r| S | dd…dd…ddd…dd…f                              |||||¦  «        } |                      |||z  ||¦  «        S )zÔ
    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   Úreshape)r9   rŒ   ÚbatchÚnum_key_value_headsÚslenrZ   s         r-   Ú	repeat_kvr’   Š   s„   € ð
 2?Ô1DÑ.€EÐ  hØ�‚z€zØÐØ! ! ! ! Q Q Q¨¨a¨a¨a°°°Ð"2Ô3×:Ò:¸5ÐBUÐW\Ð^bÐdlÑmÔm€MØ× Ò  Ð(;¸eÑ(CÀTÈ8ÑTÔTÐTr.   ç        ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingÚdropoutr`   c                 ó  — t          || j        ¦  «        }t          || j        ¦  «        }	t          j        ||                     dd¦  «        ¦  «        |z  }
|�|
|z   }
t
          j                             |
dt          j        ¬¦  «         	                    |j
        ¦  «        }
t
          j                             |
|| j        ¬¦  «        }
t          j        |
|	¦  «        }|                     dd¦  «                             ¦   «         }||
fS )Nr2   r   r0   )rb   r3   )ÚpÚtrainingr   )r’   Únum_key_value_groupsr$   Úmatmulro   r   Ú
functionalÚsoftmaxr5   r4   r3   rš   r�   Ú
contiguous)r”   r•   r–   r—   r˜   r™   rš   r`   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r-   Úeager_attention_forwardr§   –   sé   € õ ˜3 Ô ;Ñ<Ô<€JÝ˜U FÔ$?Ñ@Ô@€Lå”<  z×';Ò';¸A¸qÑ'AÔ'AÑBÔBÀWÑL€LØÐ!Ø# nÑ4ˆå”=×(Ò(¨¸2ÅUÄ]Ð(ÑSÔS×VÒVÐW\ÔWbÑcÔc€LÝ”=×(Ò(¨¸È6Ì?Ð(Ñ[Ô[€LÝ”,˜|¨\Ñ:Ô:€KØ×'Ò'¨¨1Ñ-Ô-×8Ò8Ñ:Ô:€Kà˜Ð$Ð$r.   c                 ó’   — | dd d d…f         }| ddd d…f         }t          j        | |gd¬¦  «                             d¦  «        }|S )N.r2   r   r0   ri   éþÿÿÿ)r$   ÚstackÚflatten)rs   Úx1Úx2Úrot_xs       r-   Úrotate_halfr¯   ¯   sU   € à	
ˆ3���!�ˆ8Œ€BØ	
ˆ3���1�ˆ9Œ€BÝŒK˜"˜˜b˜	 rÐ*Ñ*Ô*×2Ò2°2Ñ6Ô6€EØ€Lr.   c                 ól  — | j         }|                      ¦   «         } |                     ¦   «         }|                     |¦  «        }|                     |¦  «        }| |z  t          | ¦  «        |z  z   }||z  t          |¦  «        |z  z   }|                     |¬¦  «        |                     |¬¦  «        fS )a…  Applies Rotary Position Embedding to the query and key tensors.

    Args:
        q (`torch.Tensor`): The query tensor.
        k (`torch.Tensor`): The key tensor.
        cos (`torch.Tensor`): The cosine part of the rotary embedding.
        sin (`torch.Tensor`): The sine part of the rotary embedding.
        unsqueeze_dim (`int`, *optional*, defaults to 1):
            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
    Returns:
        `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
    r[   )r3   r_   Ú	unsqueezer¯   r4   )ÚqÚkrq   rr   Úunsqueeze_dimr3   Úq_embedÚk_embeds           r-   Úapply_rotary_pos_embr·   ·   s    € ð$ ŒG€EØ	�Š‰	Œ	€AØ	�Š‰	Œ	€AØ
�-Š-˜Ñ
&Ô
&€CØ
�-Š-˜Ñ
&Ô
&€CØ�3‰w�; q™>œ>¨CÑ/Ñ0€GØ�3‰w�; q™>œ>¨CÑ/Ñ0€GØ�:Š:˜Eˆ:Ñ"Ô" G§J¢J°U JÑ$;Ô$;Ð;Ð;r.   c                   óÒ   ‡ — e Zd ZdZddededz  fˆ fd„Z	 ddej        de	ej        ej        f         dej        dz  d	e
dz  d
ee         de	ej        ej        dz  f         fd„Zˆ xZS )ÚCohereAttentionz=Multi-headed attention from 'Attention Is All You Need' paperNrG   Ú	layer_idxc                 ót  •— t          ¦   «                              ¦   «          || _        || _        t	          |d|j        |j        z  ¦  «        | _        |j        |j        z  | _	        | j        dz  | _
        |j        | _        d| _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        | j        z  |j        |j        ¬¦  «        | _        |j        | _        | j        rPt+          |j        | j        f|j        ¬¦  «        | _        t+          |j        | j        f|j        ¬¦  «        | _        d S d S )NrZ   g      à¿Tr‚   ©r)   r*   )r!   r"   rG   rº   r\   r)   r]   rZ   r�   rž   r™   Úattention_dropoutÚ	is_causalr   r„   Úattention_biasÚq_projÚk_projÚv_projÚo_projÚuse_qk_normr   Úlayer_norm_epsÚq_normÚk_norm©r(   rG   rº   r,   s      €r-   r"   zCohereAttention.__init__Ö   s¶  ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒÝ ¨
°FÔ4FÈ&ÔJdÑ4dÑeÔeˆŒØ$*Ô$>À&ÔB\Ñ$\ˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒå”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ&¨¬Ñ6¸Ô8JÐQWÔQfð
ñ 
ô 
ˆŒð "Ô-ˆÔØÔð 	å)Ø#Ô7¸¼ÐGÈVÔMbðñ ô ˆDŒKõ *Ø#Ô7¸¼ÐGÈVÔMbðñ ô ˆDŒKˆKˆKð	ð 	r.   r9   Úposition_embeddingsr˜   Úpast_key_valuesr`   rW   c                 ó�  — |j         d d…         }g |¢d‘| j        ‘R }|                      |¦  «                             |¦  «        }|                      |¦  «                             |¦  «        }	|                      |¦  «                             |¦  «        }
| j        r*|                      |¦  «        }|                      |	¦  «        }	| 	                    dd¦  «        }|	 	                    dd¦  «        }	|
 	                    dd¦  «        }
|\  }}t          ||	||¦  «        \  }}	|�|                     |	|
| j        ¦  «        \  }	}
t          j        | j        j        t"          ¦  «        } || ||	|
|f| j        sdn| j        | j        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )Nr0   r   r2   r“   )rš   r™   )rk   rZ   rÀ   ÚviewrÁ   rÂ   rÄ   rÆ   rÇ   ro   r·   Úupdaterº   r   Úget_interfacerG   Ú_attn_implementationr§   r�   r½   r™   rŽ   r¢   rÃ   )r(   r9   rÉ   r˜   rÊ   r`   Úinput_shapeÚhidden_shapeÚquery_statesr£   r¤   rq   rr   Úattention_interfacer¦   r¥   s                   r-   r<   zCohereAttention.forwardö   sù  € ð $Ô)¨#¨2¨#Ô.ˆØ8˜Ð8 bÐ8¨$¬-Ð8Ð8ˆà—{’{ =Ñ1Ô1×6Ò6°|ÑDÔDˆØ—[’[ Ñ/Ô/×4Ò4°\ÑBÔBˆ
Ø—{’{ =Ñ1Ô1×6Ò6°|ÑDÔDˆàÔð 	1ØŸ;š; |Ñ4Ô4ˆLØŸš ZÑ0Ô0ˆJà#×-Ò-¨a°Ñ3Ô3ˆØ×)Ò)¨!¨QÑ/Ô/ˆ
Ø#×-Ò-¨a°Ñ3Ô3ˆà&‰ˆˆSÝ#7¸ÀjÐRUÐWZÑ#[Ô#[Ñ ˆ�jàÐ&Ø'6×'=Ò'=¸jÈ,ÐX\ÔXfÑ'gÔ'gÑ$ˆJ˜å(?Ô(MØŒKÔ,Õ.Eñ)
ô )
Ðð %8Ð$7ØØØØØð	%
ð  $œ}ÐH�C�C°$Ô2HØ”Lð	%
ð 	%
ð ð	%
ð 	%
Ñ!ˆ�\ð *�kÔ)Ð;¨;Ð;¸Ð;Ð;Ð;×FÒFÑHÔHˆØ—k’k +Ñ.Ô.ˆØ˜LÐ(Ð(r.   ry   )r>   r?   r@   Ú__doc__r   Úintr"   r$   r|   r{   r   r   r   r<   rA   rB   s   @r-   r¹   r¹   Ó   sç   ø€ € € € € ØGÐGðð ˜|ð ¸¸d¹
ð ð ð ð ð ð ðJ )-ð.)ð .)à”|ð.)ð # 5¤<°´Ð#=Ô>ð.)ð œ tÑ+ð	.)ð
  ™ð.)ð Ð-Ô.ð.)ð 
ˆuŒ|˜Uœ\¨DÑ0Ð0Ô	1ð.)ð .)ð .)ð .)ð .)ð .)ð .)ð .)r.   r¹   c                   óÒ   ‡ — e Zd Zdedefˆ fd„Z	 	 	 	 	 ddej        dej        dz  dej        dz  d	e	dz  d
e
dz  deej        ej        f         dz  dee         dej        fd„Zˆ xZS )ÚCohereDecoderLayerrG   rº   c                 óô   •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        |j        ¬¦  «        | _	        d S )N)rG   rº   r¼   )
r!   r"   r)   r¹   Ú	self_attnr   Úmlpr   rÅ   Úinput_layernormrÈ   s      €r-   r"   zCohereDecoderLayer.__init__(  si   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔÝ(°À)ÐLÑLÔLˆŒÝ˜VÑ$Ô$ˆŒÝ.¸FÔ<NÐU[ÔUjÐkÑkÔkˆÔÐÐr.   NFr9   r˜   rt   rÊ   Ú	use_cacherÉ   r`   rW   c           
      óœ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }	}
|                      |¦  «        }||	z   |z   }|S )a¼  
        Args:
            hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
            attention_mask (`torch.FloatTensor`, *optional*):
                attention mask of size `(batch_size, sequence_length)` if flash attention is used or `(batch_size, 1,
                query_sequence_length, key_sequence_length)` if default attention is used.
            past_key_values (`Cache`, *optional*): cached past key and value projection states
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
            use_cache (`bool`, *optional*):
                If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
                (see `past_key_values`).
            position_embeddings (`tuple[torch.FloatTensor, torch.FloatTensor]`, *optional*):
                Tuple containing the cosine and sine positional embeddings of shape `(batch_size, seq_len, head_dim)`,
                with `head_dim` being the embedding dimension of each attention head.
        )r9   r˜   rt   rÊ   rÜ   rÉ   © )rÛ   rÙ   rÚ   )r(   r9   r˜   rt   rÊ   rÜ   rÉ   r`   ÚresidualÚhidden_states_attentionÚ_Úhidden_states_mlps               r-   r<   zCohereDecoderLayer.forward/  s†   € ð6 !ˆØ×,Ò,¨]Ñ;Ô;ˆà%3 T¤^ð &
Ø'Ø)Ø%Ø+ØØ 3ð&
ð &
ð ð&
ð &
Ñ"Ð ð !ŸHšH ]Ñ3Ô3ÐØ Ð#:Ñ:Ð=NÑNˆØÐr.   )NNNFN)r>   r?   r@   r   rÕ   r"   r$   r|   Ú
LongTensorr   Úboolr{   r   r   r<   rA   rB   s   @r-   r×   r×   '  sÿ   ø€ € € € € ðl˜|ð l¸ð lð lð lð lð lð lð /3Ø04Ø(,Ø!&ØHLð*ð *à”|ð*ð œ tÑ+ð*ð Ô&¨Ñ-ð	*ð
  ™ð*ð ˜$‘;ð*ð # 5¤<°´Ð#=Ô>ÀÑEð*ð Ð-Ô.ð*ð 
Œð*ð *ð *ð *ð *ð *ð *ð *r.   r×   c                   óL   — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZdS )ÚCoherePreTrainedModelrG   ÚmodelTr×   rÊ   )r9   Ú
attentionsN)r>   r?   r@   r   Ú__annotations__Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendr×   r¹   Ú_can_record_outputsrÞ   r.   r-   ræ   ræ   \  sl   € € € € € € àÐÐÑØÐØ&*Ð#Ø-Ð.ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà+Ø%ðð ÐÐÐr.   ræ   c                   óâ   ‡ — e Zd Zdefˆ fd„Zeee	 	 	 	 	 	 ddej	        dz  dej
        dz  dej	        dz  dedz  dej        dz  d	edz  d
ee         defd„¦   «         ¦   «         ¦   «         Zˆ xZS )ÚCohereModelrG   c                 óÞ  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ‰j        ¬¦  «        | _        t!          ‰¬¦  «        | _        d| _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS rÞ   )r×   )Ú.0rº   rG   s     €r-   ú
<listcomp>z(CohereModel.__init__.<locals>.<listcomp>x  s$   ø€ ÐdÐdÐd°yÕ ¨	Ñ2Ô2ÐdÐdÐdr.   r¼   ©rG   F)r!   r"   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr)   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr   rÅ   ÚnormrD   Ú
rotary_embÚgradient_checkpointingÚ	post_initrŠ   s    `€r-   r"   zCohereModel.__init__q  sÔ   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØdÐdÐdÐdÅEÈ&ÔJbÑDcÔDcÐdÑdÔdñ
ô 
ˆŒõ $°Ô1CÈ&ÔJ_Ð`Ñ`Ô`ˆŒ	Ý/°vÐ>Ñ>Ô>ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr.   NÚ	input_idsr˜   rt   rÊ   Úinputs_embedsrÜ   r`   rW   c           
      óH  — |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }t          | j        ||||¬¦  «        }	|}
|                      |
|¬¦  «        }| j        d | j        j        …         D ]} ||
f|	||||dœ|¤Ž}
Œ|                      |
¦  «        }
t          |
|¬	¦  «        S )
Nz:You must specify exactly one of input_ids or inputs_embedsrú   r   r   )rE   )rG   r	  r˜   rÊ   rt   )rt   )r˜   rÉ   rt   rÊ   rÜ   )Úlast_hidden_staterÊ   )Ú
ValueErrorrÿ   r   rG   Úget_seq_lengthr$   r^   rk   rE   r±   r
   r  r  r  r  r   )r(   r  r˜   rt   rÊ   r	  rÜ   r`   Úpast_seen_tokensÚcausal_maskr9   rÉ   Údecoder_layers                r-   r<   zCohereModel.forward�  sŠ  € ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàÐ Ø*.×*;Ò*;¸IÑ*FÔ*FˆMàð 	?˜Ð0Ý*°$´+Ð>Ñ>Ô>ˆOàÐØCRÐC^˜×=Ò=Ñ?Ô?Ð?ÐdeÐÝ œ<¨Ô(;¸AÔ(>À}ÔG[Ð\Ñ\Ô\Ð_oÑoˆLØ'×1Ò1°!Ñ4Ô4ˆLå(Ø”;Ø'Ø)Ø+Ø%ð
ñ 
ô 
ˆð &ˆØ"Ÿošo¨mÈ,˜oÑWÔWÐà!œ[Ð)H¨4¬;Ô+HÐ)HÔIð 		ð 		ˆMØ)˜MØðà*Ø$7Ø)Ø /Ø#ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝ&Ø+Ø+ð
ñ 
ô 
ð 	
r.   )NNNNNN)r>   r?   r@   r   r"   r   r   r   r$   rã   r|   r   ÚFloatTensorrä   r   r   r   r<   rA   rB   s   @r-   rõ   rõ   o  s  ø€ € € € € ð˜|ð ð ð ð ð ð ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð2
ð 2
àÔ# dÑ*ð2
ð œ tÑ+ð2
ð Ô&¨Ñ-ð	2
ð
  ™ð2
ð Ô(¨4Ñ/ð2
ð ˜$‘;ð2
ð Ð+Ô,ð2
ð 
!ð2
ð 2
ð 2
ñ „^ñ „_ñ  Ôð2
ð 2
ð 2
ð 2
ð 2
r.   rõ   c                   ó   ‡ — e Zd ZddiZddiZddgdgfiZddiZˆ fd„Zee		 	 	 	 	 	 	 	 dde
j        d	z  de
j        d	z  de
j        d	z  ded	z  de
j        d	z  de
j        d	z  ded	z  dee
j        z  dee         defd„¦   «         ¦   «         Zˆ xZS )ÚCohereForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr9   ÚlogitsÚkeep_full_weightc                 ó.  •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |j	        | _	        |j
        | _
        |                      ¦   «          d S r�   )r!   r"   rõ   rç   rý   r   r„   r)   r  Úlogit_scaleÚtie_word_embeddingsr  rŠ   s     €r-   r"   zCohereForCausalLM.__init__À  s€   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ý  Ñ(Ô(ˆŒ
Ø Ô+ˆŒÝ”y Ô!3°VÔ5FÈUÐSÑSÔSˆŒØ!Ô-ˆÔØ#)Ô#=ˆÔ ð 	�ŠÑÔÐÐÐr.   Nr   r  r˜   rt   rÊ   r	  ÚlabelsrÜ   Úlogits_to_keepr`   rW   c	           
      ód  —  | j         d||||||dœ|	¤Ž}
|
j        }t          |t          ¦  «        rt	          | d¦  «        n|}|                      |dd…|dd…f         ¦  «        }|| j        z  }d}|� | j        d||| j        j	        dœ|	¤Ž}t          |||
j        |
j        |
j        ¬¦  «        S )aÕ  
        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˜   rt   rÊ   r	  rÜ   N)r  r  rý   )Úlossr  rÊ   r9   rè   rÞ   )rç   r  rl   rÕ   Úslicer  r  Úloss_functionrG   rý   r   rÊ   r9   rè   )r(   r  r˜   rt   rÊ   r	  r  rÜ   r  r`   Úoutputsr9   Úslice_indicesr  r  s                  r-   r<   zCohereForCausalLM.forwardË  s  € ð> ,6¨4¬:ð ,
ØØ)Ø%Ø+Ø'Øð,
ð ,
ð ð,
ð ,
ˆð  Ô1ˆÝ8BÀ>ÕSVÑ8WÔ8WÐk�˜~˜o¨tÑ4Ô4Ð4Ð]kˆØ—’˜m¨A¨A¨A¨}¸a¸a¸aÐ,?Ô@ÑAÔAˆØ˜$Ô*Ñ*ˆàˆØÐØ%�4Ô%Ðp¨V¸FÈtÌ{ÔOeÐpÐpÐioÐpÐpˆDå%ØØØ#Ô3Ø!Ô/ØÔ)ð
ñ 
ô 
ð 	
r.   )NNNNNNNr   )r>   r?   r@   Ú_tied_weights_keysÚ_tp_planÚ_pp_planÚ
_fsdp_planr"   r   r   r$   rã   r|   r   r  rä   rÕ   r   r   r   r<   rA   rB   s   @r-   r  r  ¹  sV  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€HØÐ/Ð0€Jð	ð 	ð 	ð 	ð 	ð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ð6
ð 6
àÔ# dÑ*ð6
ð œ tÑ+ð6
ð Ô&¨Ñ-ð	6
ð
  ™ð6
ð Ô(¨4Ñ/ð6
ð Ô  4Ñ'ð6
ð ˜$‘;ð6
ð ˜eœlÑ*ð6
ð Ð+Ô,ð6
ð 
 ð6
ð 6
ð 6
ñ „^ñ Ôð6
ð 6
ð 6
ð 6
ð 6
r.   r  )r  rõ   ræ   )r“   )r   ):Úcollections.abcr   r$   r   Úactivationsr   Úcache_utilsr   r   Ú
generationr	   Úmasking_utilsr
   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.deprecationr   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_coherer   ÚModuler   rD   r   r|   rÕ   r’   r_   r§   r¯   r·   r¹   r×   ræ   rõ   r  Ú__all__rÞ   r.   r-   ú<module>r9     sò  ðð: %Ð $Ð $Ð $Ð $Ð $à €€€Ø Ð Ð Ð Ð Ð à !Ð !Ð !Ð !Ð !Ð !Ø .Ð .Ð .Ð .Ð .Ð .Ð .Ð .Ø )Ð )Ð )Ð )Ð )Ð )Ø /Ð /Ð /Ð /Ð /Ð /Ø BÐ BÐ BÐ BÐ BÐ BØ 9Ð 9Ð 9Ð 9Ð 9Ð 9Ø OÐ OÐ OÐ OÐ OÐ OÐ OÐ OØ KÐ KÐ KÐ KÐ KÐ KÐ KÐ KØ FÐ FÐ FÐ FÐ FÐ FÐ FÐ FØ &Ð &Ð &Ð &Ð &Ð &Ø IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ 0Ð 0Ð 0Ð 0Ð 0Ð 0Ø GÐ GÐ GÐ GÐ GÐ GÐ GÐ GØ 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø .Ð .Ð .Ð .Ð .Ð .ð-ð -ð -ð -ð -�b”iñ -ô -ð -ð"3<ð 3<ð 3<ð 3<ð 3<˜BœIñ 3<ô 3<ð 3<ðlð ð ð ð �”	ñ ô ð ð 	U˜Uœ\ð 	U°#ð 	U¸%¼,ð 	Uð 	Uð 	Uð 	Uð& ð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð ð%ð ð%ð Ð'Ô(ð%ð %ð %ð %ð2ð ð ð<ð <ð <ð <ð8Q)ð Q)ð Q)ð Q)ð Q)�b”iñ Q)ô Q)ð Q)ðh2ð 2ð 2ð 2ð 2Ð3ñ 2ô 2ð 2ðj ðð ð ð ð ˜Oñ ô ñ „ðð$ ðF
ð F
ð F
ð F
ð F
Ð'ñ F
ô F
ñ „ðF
ðR ðI
ð I
ð I
ð I
ð I
Ð-¨ñ I
ô I
ñ „ðI
ðX HÐ
GÐ
G€€€r.   