§
    ‚Štj#U  ã                   óv  — d dl mZ d dlmZ d dl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 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mZ ddlmZmZ ddlm Z m!Z! ddl"m#Z# ddl$m%Z%m&Z& ddl'm(Z(m)Z) ddl*m+Z+ ddl,m-Z-  ed¦  «         G d„ dej.        ¦  «        ¦   «         Z/ G d„ dej.        ¦  «        Z0dej1        de2dej1        fd„Z3	 d:dej.        d ej1        d!ej1        d"ej1        d#ej1        dz  d$e4d%e4d&e#e         fd'„Z5 ed(¦  «        d;d)„¦   «         Z6d*„ Z7 ee6¦  «         G d+„ d,ej.        ¦  «        ¦   «         Z8 G d-„ d.ej.        ¦  «        Z9 G d/„ d0e¦  «        Z:e% G d1„ d2e!¦  «        ¦   «         Z;e% G d3„ d4e;¦  «        ¦   «         Z<e% G d5„ d6e;e¦  «        ¦   «         Z= G d7„ d8ee;¦  «        Z>g d9¢Z?dS )<é    )ÚCallable)ÚOptionalN)ÚTransformersKwargsé   )ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_forward_from_hubÚuse_kernel_func_from_hubÚuse_kernelized_func)Úcreate_causal_mask)Ú GenericForSequenceClassificationÚGradientCheckpointingLayer)ÚBaseModelOutputWithPastÚCausalLMOutputWithPast)ÚROPE_INIT_FUNCTIONSÚdynamic_rope_update)ÚALL_ATTENTION_FUNCTIONSÚPreTrainedModel)ÚUnpack)Úauto_docstringÚcan_return_tuple)Úmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputsé   )ÚOlmo2ConfigÚRMSNormc                   óF   ‡ — e Zd Zddeddfˆ fd„Zdej        fd„Zd„ Zˆ xZ	S )	ÚOlmo2RMSNormç�íµ ÷Æ°>ÚepsÚreturnNc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z;
        Olmo2RMSNorm is equivalent to T5LayerNorm
        N)ÚsuperÚ__init__ÚnnÚ	ParameterÚtorchÚonesÚweightÚvariance_epsilon)ÚselfÚhidden_sizer#   Ú	__class__s      €úf/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/olmo2/modeling_olmo2.pyr'   zOlmo2RMSNorm.__init__4   sD   ø€ õ 	‰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d¬¦  «        }|t          j        || j        z   ¦  «        z  }| j        |z                       |¦  «        S )Né   éÿÿÿÿT)Úkeepdim)	ÚdtypeÚtor*   Úfloat32ÚpowÚmeanÚrsqrtr-   r,   )r.   Úhidden_statesÚinput_dtypeÚvariances       r1   ÚforwardzOlmo2RMSNorm.forward<   s|   € Ø#Ô)ˆØ%×(Ò(­¬Ñ7Ô7ˆØ ×$Ò$ QÑ'Ô'×,Ò,¨R¸Ð,Ñ>Ô>ˆØ%­¬°H¸tÔ?TÑ4TÑ(UÔ(UÑUˆØ”˜mÑ+×/Ò/°Ñ<Ô<Ð<r2   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)Útupler,   Úshaper-   )r.   s    r1   Ú
extra_reprzOlmo2RMSNorm.extra_reprC   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr2   )r"   )
Ú__name__Ú
__module__Ú__qualname__Úfloatr'   r*   ÚTensorr@   rD   Ú__classcell__©r0   s   @r1   r!   r!   2   sƒ   ø€ € € € € ð$ð $¨ð $¸$ð $ð $ð $ð $ð $ð $ð=¨¬ð =ð =ð =ð =ðJð Jð Jð Jð Jð Jð Jr2   r!   c                   óÔ   ‡ — e Zd ZU ej        ed<   ddefˆ fd„Ze	 	 	 ddedz  de	d         de
dz  ded	ef         fd
„¦   «         Z ej        ¦   «         ed„ ¦   «         ¦   «         Zˆ xZS )ÚOlmo2RotaryEmbeddingÚinv_freqNÚconfigc                 ó²  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        | j        j        d         | _        | j        }| j        dk    rt          | j                 } || j        |¦  «        \  }| _
        |                      d|d¬¦  «         |                      d|                     ¦   «         d¬¦  «         d S )NÚ	rope_typeÚdefaultrN   F)Ú
persistentÚoriginal_inv_freq)r&   r'   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrO   Úrope_parametersrQ   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r.   rO   ÚdeviceÚrope_init_fnrN   r0   s        €r1   r'   zOlmo2RotaryEmbedding.__init__J   sÊ   ø€ Ý‰Œ×ÒÑÔÐØ"(Ô"@ˆÔØ$*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(à×Ò˜Z¨¸eÐÑDÔDÐDØ×ÒÐ0°(·.².Ñ2BÔ2BÈuÐÑUÔUÐUÐUÐUr2   r]   ztorch.deviceÚseq_lenr$   ztorch.Tensorc                 óü   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «                             |t          j        ¬¦  «        |z  z  z  }||fS )	a¨  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetaÚhead_dimNg      ð?r   r4   )r7   )r]   r7   )	rX   Úgetattrr/   Únum_attention_headsr*   ÚarangeÚint64r8   rH   )rO   r]   r_   ÚbaseÚdimÚattention_factorrN   s          r1   rY   z4Olmo2RotaryEmbedding.compute_default_rope_parametersZ   sŒ   € ð& Ô% lÔ3ˆÝ�f˜j¨$Ñ/Ô/Ðc°6Ô3EÈÔIcÑ3cˆàÐð Ø•U”\ ! S¨!µ5´;Ð?Ñ?Ô?×BÒBÈ&ÕX]ÔXcÐBÑdÔdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r2   c                 óê  — | j         d d d …d f                              ¦   «                              |j        d         dd¦  «                             |j        ¦  «        }|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        ||fd¬	¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   ||	fS )
Nr   r5   r   ÚmpsÚcpuF)Údevice_typeÚenabledr4   ©rh   )rN   rH   ÚexpandrC   r8   r]   Ú
isinstanceÚtypeÚstrr   Ú	transposer*   ÚcatÚcosrZ   Úsin)
r.   ÚxÚposition_idsÚinv_freq_expandedÚposition_ids_expandedrm   ÚfreqsÚembrv   rw   s
             r1   r@   zOlmo2RotaryEmbedding.forwardx   s•  € ð !œM¨$°°°°4¨-Ô8×>Ò>Ñ@Ô@×GÒGÈÔHZÐ[\ÔH]Ð_aÐcdÑeÔe×hÒhÐijÔiqÑrÔrÐØ ,¨Q¨Q¨Q°°a°a°a¨ZÔ 8× >Ò >Ñ @Ô @Ðå'1°!´(´-ÅÑ'EÔ'EÐkÈ!Ì(Ì-Ð[`ÒJ`ÐJ`�a”h”m�mÐfkˆÝ¨¸UÐCÑCÔCð 	5ð 	5Ø&×,Ò,Ñ.Ô.Ð1F×1LÒ1LÑ1NÔ1NÑN×YÒYÐZ[Ð]^Ñ_Ô_ˆEÝ”)˜U E˜N°Ð3Ñ3Ô3ˆCØ—'’'‘)”)˜dÔ4Ñ4ˆCØ—'’'‘)”)˜dÔ4Ñ4ˆCð		5ð 	5ð 	5ñ 	5ô 	5ð 	5ð 	5ð 	5ð 	5ð 	5ð 	5øøøð 	5ð 	5ð 	5ð 	5ð
 �Cˆxˆs   ÃBE&Å&E*Å-E*©N)NNN)rE   rF   rG   r*   rI   Ú__annotations__r   r'   Ústaticmethodr   ÚintrB   rH   rY   Úno_gradr   r@   rJ   rK   s   @r1   rM   rM   G   sù   ø€ € € € € € ØŒlÐÐÑðVð V˜{ð Vð Vð Vð Vð Vð Vð  à%)Ø+/Ø"ð*ð *Ø˜dÑ"ð*à˜Ô(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ô	%ð	*ð *ð *ñ „\ð*ð: €U„]�_„_Øð
ð 
ñ Ôñ „_ð
ð 
ð 
ð 
ð 
r2   rM   r=   Ún_repr$   c                 ó¸   — | j         \  }}}}|dk    r| S | dd…dd…ddd…dd…f                              |||||¦  «        } |                      |||z  ||¦  «        S )zÔ
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r   N)rC   rp   Úreshape)r=   rƒ   ÚbatchÚnum_key_value_headsÚslenrb   s         r1   Ú	repeat_kvr‰   ‡   s„   € ð
 2?Ô1DÑ.€EÐ  hØ�‚z€zØÐØ! ! ! ! Q Q Q¨¨a¨a¨a°°°Ð"2Ô3×:Ò:¸5ÐBUÐW\Ð^bÐdlÑmÔm€MØ× Ò  Ð(;¸eÑ(CÀTÈ8ÑTÔTÐTr2   ç        ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingÚdropoutÚkwargsc                 ó  — t          || j        ¦  «        }t          || j        ¦  «        }	t          j        ||                     dd¦  «        ¦  «        |z  }
|�|
|z   }
t
          j                             |
dt          j        ¬¦  «         	                    |j
        ¦  «        }
t
          j                             |
|| j        ¬¦  «        }
t          j        |
|	¦  «        }|                     dd¦  «                             ¦   «         }||
fS )Nr4   r   r5   )rh   r7   )ÚpÚtrainingr   )r‰   Únum_key_value_groupsr*   Úmatmulrt   r(   Ú
functionalÚsoftmaxr9   r8   r7   r‘   r•   Ú
contiguous)r‹   rŒ   r�   rŽ   r�   r�   r‘   r’   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r1   Úeager_attention_forwardrŸ   “   sé   € õ ˜3 Ô ;Ñ<Ô<€JÝ˜U FÔ$?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$Ð$r2   Úrotary_pos_embc                 ó&  — | j         |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.
    )r7   Ú	unsqueezeÚrotate_halfr8   )	ÚqÚkrv   rw   Úunsqueeze_dimÚq_typeÚk_typeÚq_embedÚk_embeds	            r1   Úapply_rotary_pos_embr«   ¬   sˆ   € ð& ”W˜aœgˆF€FØ
�-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:�fÑÔ˜wŸzšz¨&Ñ1Ô1Ð1Ð1r2   c                 óœ   — | dd| j         d         dz  …f         }| d| j         d         dz  d…f         }t          j        | |fd¬¦  «        S )z*Rotates half the hidden dims of the input..Nr5   r4   ro   )rC   r*   ru   )rx   Úx1Úx2s      r1   r£   r£   Ç   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'r2   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Olmo2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperNrO   Ú	layer_idxc                 óJ  •— 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        ¬¦  «        | _        t)          |j        | j        z  |j        ¦  «        | _        t)          |j        | j        z  |j        ¦  «        | _        d S )Nrb   g      à¿T©Úbias)r&   r'   rO   r±   rc   r/   rd   rb   r‡   r–   r�   Úattention_dropoutÚ	is_causalr(   ÚLinearÚattention_biasÚq_projÚk_projÚv_projÚo_projr!   Úrms_norm_epsÚq_normÚk_norm©r.   rO   r±   r0   s      €r1   r'   zOlmo2Attention.__init__Ò   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$\ˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒå”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ&¨¬Ñ6¸Ô8JÐQWÔQfð
ñ 
ô 
ˆŒõ # 6Ô#=ÀÄÑ#MÈvÔObÑcÔcˆŒÝ" 6Ô#=ÀÄÑ#MÈvÔObÑcÔcˆŒˆˆr2   r=   Úposition_embeddingsr�   Úpast_key_valuesr’   r$   c                 óz  — |j         d d…         }g |¢d‘| 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 )Nr5   r   r4   rŠ   )r‘   r�   )rC   rb   r¾   r¹   r¿   rº   r»   Úviewrt   r«   Úupdater±   r   Úget_interfacerO   Ú_attn_implementationrŸ   r•   rµ   r�   r…   rš   r¼   )r.   r=   rÁ   r�   rÂ   r’   Úinput_shapeÚhidden_shapeÚquery_statesr›   rœ   rv   rw   Úattention_interfacerž   r�   s                   r1   r@   zOlmo2Attention.forwardë   sâ  € ð $Ô)¨#¨2¨#Ô.ˆØ8˜Ð8 bÐ8¨$¬-Ð8Ð8ˆà—{’{ 4§;¢;¨}Ñ#=Ô#=Ñ>Ô>ˆØ—[’[ §¢¨]Ñ!;Ô!;Ñ<Ô<ˆ
Ø—{’{ =Ñ1Ô1ˆà#×(Ò(¨Ñ6Ô6×@Ò@ÀÀAÑFÔFˆØ—_’_ \Ñ2Ô2×<Ò<¸QÀÑBÔBˆ
Ø#×(Ò(¨Ñ6Ô6×@Ò@ÀÀAÑFÔFˆ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(r2   r~   )rE   rF   rG   Ú__doc__r   r�   r'   r*   rI   rB   r   r   r   r@   rJ   rK   s   @r1   r°   r°   Î   sï   ø€ € € € € àGÐGðdð d˜{ð d°s¸T±zð dð dð dð dð dð dð< )-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 *)r2   r°   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚOlmo2MLPc                 ó˜  •— t          ¦   «                              ¦   «          || _        |j        | _        |j        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _	        t          |j                 | _        d S ©NFr³   )r&   r'   rO   r/   Úintermediate_sizer(   r·   Ú	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©r.   rO   r0   s     €r1   r'   zOlmo2MLP.__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r2   c                 ó¨   — |                       |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        }|S r~   )rÔ   rÖ   rÒ   rÓ   )r.   rx   rÔ   s      r1   r@   zOlmo2MLP.forward#  sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr2   )rE   rF   rG   r'   r@   rJ   rK   s   @r1   rÎ   rÎ     sG   ø€ € € € € ð0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð r2   rÎ   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Olmo2DecoderLayerrO   r±   c                 ó4  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        |j        ¬¦  «        | _	        t          |j        |j        ¬¦  «        | _
        d S )N)rO   r±   ©r#   )r&   r'   r/   r°   Ú	self_attnrÎ   Úmlpr!   r½   Úpost_attention_layernormÚpost_feedforward_layernormrÀ   s      €r1   r'   zOlmo2DecoderLayer.__init__)  sƒ   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔÝ'¨vÀÐKÑKÔKˆŒå˜FÑ#Ô#ˆŒÝ(4°VÔ5GÈVÔM`Ð(aÑ(aÔ(aˆÔ%Ý*6°vÔ7IÈvÔObÐ*cÑ*cÔ*cˆÔ'Ð'Ð'r2   NFr=   r�   ry   rÂ   Ú	use_cacherÁ   r’   r$   c           
      óÎ   — |} | j         d||||||dœ|¤Ž\  }}	|                      |¦  «        }||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r=   r�   ry   rÂ   rá   rÁ   © )rÝ   rß   rÞ   rà   )
r.   r=   r�   ry   rÂ   rá   rÁ   r’   ÚresidualÚ_s
             r1   r@   zOlmo2DecoderLayer.forward2  s¡   € ð !ˆØ)˜4œ>ð 
Ø'Ø)Ø%Ø+ØØ 3ð
ð 
ð ð
ð 
Ñˆ�qð ×5Ò5°mÑDÔDˆØ  =Ñ0ˆð !ˆØŸš Ñ/Ô/ˆØ×7Ò7¸ÑFÔFˆØ  =Ñ0ˆØÐr2   )NNNFN)rE   rF   rG   r   r�   r'   r*   rI   Ú
LongTensorr   ÚboolrB   r   r   r@   rJ   rK   s   @r1   rÚ   rÚ   (  sÿ   ø€ € € € € ðd˜{ð d°sð dð dð dð dð dð dð /3Ø04Ø(,Ø!&ØHLðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r2   rÚ   c                   óL   — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZdS )ÚOlmo2PreTrainedModelrO   ÚmodelTrÚ   rÂ   )r=   Ú
attentionsN)rE   rF   rG   r   r   Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendrÚ   r°   Ú_can_record_outputsrã   r2   r1   ré   ré   Q  sl   € € € € € € àÐÐÑØÐØ&*Ð#Ø,Ð-ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà*Ø$ðð ÐÐÐr2   ré   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
Olmo2ModelrO   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 rã   )rÚ   )Ú.0r±   rO   s     €r1   ú
<listcomp>z'Olmo2Model.__init__.<locals>.<listcomp>m  s$   ø€ ÐcÐcÐc°iÕ˜v yÑ1Ô1ÐcÐcÐcr2   rÜ   ©rO   F)r&   r'   Úpad_token_idÚpadding_idxÚ
vocab_sizer(   Ú	Embeddingr/   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr!   r½   ÚnormrM   Ú
rotary_embÚgradient_checkpointingÚ	post_initr×   s    `€r1   r'   zOlmo2Model.__init__f  sÔ   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØcÐcÐcÐcÅ5ÈÔIaÑCbÔCbÐcÑcÔcñ
ô 
ˆŒõ ! Ô!3¸Ô9LÐMÑMÔMˆŒ	Ý.°fÐ=Ñ=Ô=ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr2   NÚ	input_idsr�   ry   rÂ   Úinputs_embedsrá   r’   r$   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_embedsrü   r   r   )r]   )rO   r  r�   rÂ   ry   )ry   )r�   rÁ   ry   rÂ   rá   )Úlast_hidden_staterÂ   )Ú
ValueErrorr  r	   rO   Úget_seq_lengthr*   re   rC   r]   r¢   r   r  r  r  r  r   )r.   r
  r�   ry   rÂ   r  rá   r’   Úpast_seen_tokensÚcausal_maskr=   rÁ   Údecoder_layers                r1   r@   zOlmo2Model.forwardv  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$7Ø)Ø /Ø#ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝ&Ø+Ø+ð
ñ 
ô 
ð 	
r2   )NNNNNN)rE   rF   rG   r   r'   r   r   r   r*   ræ   rI   r   ÚFloatTensorrç   r   r   r   r@   rJ   rK   s   @r1   r÷   r÷   d  s  ø€ € € € € ð˜{ð ð ð ð ð ð ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð2
ð 2
àÔ# dÑ*ð2
ð œ tÑ+ð2
ð Ô&¨Ñ-ð	2
ð
  ™ð2
ð Ô(¨4Ñ/ð2
ð ˜$‘;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
r2   r÷   c                   ó  ‡ — e Zd ZddiZddiZddgdgf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Olmo2ForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr=   Úlogitsc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S rÐ   )
r&   r'   r÷   rê   rÿ   r(   r·   r/   r  r	  r×   s     €r1   r'   zOlmo2ForCausalLM.__init__´  sj   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ð 	�ŠÑÔÐÐÐr2   Nr   r
  r�   ry   rÂ   r  Úlabelsrá   Úlogits_to_keepr’   r$   c	           
      óP  —  | j         d||||||dœ|	¤Ž}
|
j        }t          |t          ¦  «        rt	          | d¦  «        n|}|                      |dd…|dd…f         ¦  «        }d}|� | j        d||| j        j        dœ|	¤Ž}t          |||
j
        |
j        |
j        ¬¦  «        S )aÏ  
        Example:

        ```python
        >>> from transformers import AutoTokenizer, Olmo2ForCausalLM

        >>> model = Olmo2ForCausalLM.from_pretrained("meta-olmo2/Olmo2-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-olmo2/Olmo2-2-7b-hf")

        >>> 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�   ry   rÂ   r  rá   N)r  r  rÿ   )Úlossr  rÂ   r=   rë   rã   )rê   r  rq   r�   Úslicer  Úloss_functionrO   rÿ   r   rÂ   r=   rë   )r.   r
  r�   ry   rÂ   r  r  rá   r  r’   Úoutputsr=   Úslice_indicesr  r  s                  r1   r@   zOlmo2ForCausalLM.forward½  sô   € ð> ,6¨4¬:ð ,
ØØ)Ø%Ø+Ø'Øð,
ð ,
ð ð,
ð ,
ˆð  Ô1ˆå8BÀ>ÕSVÑ8WÔ8WÐk�˜~˜o¨tÑ4Ô4Ð4Ð]kˆØ—’˜m¨A¨A¨A¨}¸a¸a¸aÐ,?Ô@ÑAÔAˆ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 	
r2   )NNNNNNNr   )rE   rF   rG   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr'   r   r   r*   ræ   rI   r   r  rç   r�   r   r   r   r@   rJ   rK   s   @r1   r  r  ®  sK  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hð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 ˜$‘;ð6
ð ˜eœlÑ*ð6
ð Ð+Ô,ð6
ð 
 ð6
ð 6
ð 6
ñ „^ñ Ôð6
ð 6
ð 6
ð 6
ð 6
r2   r  c                   ó   — e Zd ZdS )ÚOlmo2ForSequenceClassificationN)rE   rF   rG   rã   r2   r1   r&  r&  ø  s   € € € € € Ø€Dr2   r&  )r  r&  r÷   ré   )rŠ   )r   )@Úcollections.abcr   Útypingr   r*   Útorch.nnr(   Útransformers.utils.genericr   Úactivationsr   Úcache_utilsr   r	   Ú
generationr
   Úintegrationsr   r   r   Úmasking_utilsr   Úmodeling_layersr   r   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_olmo2r   ÚModuler!   rM   rI   r�   r‰   rH   rŸ   r«   r£   r°   rÎ   rÚ   ré   r÷   r  r&  Ú__all__rã   r2   r1   ú<module>r;     s�  ðð4 %Ð $Ð $Ð $Ð $Ð $Ø Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð à 9Ð 9Ð 9Ð 9Ð 9Ð 9à !Ð !Ð !Ð !Ð !Ð !Ø .Ð .Ð .Ð .Ð .Ð .Ð .Ð .Ø )Ð )Ð )Ð )Ð )Ð )Ø fÐ fÐ fÐ fÐ fÐ fÐ fÐ fÐ fÐ fØ /Ð /Ð /Ð /Ð /Ð /Ø [Ð [Ð [Ð [Ð [Ð [Ð [Ð [Ø 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 5Ð 5Ð 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø GÐ GÐ GÐ GÐ GÐ GÐ GÐ GØ 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø ,Ð ,Ð ,Ð ,Ð ,Ð ,ð Ð˜YÑ'Ô'ðJð Jð Jð Jð J�2”9ñ Jô Jñ (Ô'ðJð(=ð =ð =ð =ð =˜2œ9ñ =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*Ñ+Ô+ð2ð 2ð 2ñ ,Ô+ð2ð4(ð (ð (ð ÐÐ)Ñ*Ô*ðF)ð F)ð F)ð F)ð F)�R”Yñ F)ô F)ñ +Ô*ðF)ðRð ð ð ð ˆrŒyñ ô ð ð &ð &ð &ð &ð &Ð2ñ &ô &ð &ðR ðð ð ð ð ˜?ñ ô ñ „ðð$ ðF
ð F
ð F
ð F
ð F
Ð%ñ F
ô F
ñ „ðF
ðR ðF
ð F
ð F
ð F
ð F
Ð+¨_ñ F
ô F
ñ „ðF
ðR	ð 	ð 	ð 	ð 	Ð%EÐG[ñ 	ô 	ð 	ð gÐ
fÐ
f€€€r2   