§
    ‚Štj¾]  ã                   ó~  — 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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$m%Z% ddl&m'Z'm(Z( ddl)m*Z*m+Z+m,Z, ddl-m.Z. ddl/m0Z0  ed¦  «         G d„ dej1        ¦  «        ¦   «         Z2dej3        de4dej3        fd„Z5	 d:dej1        dej3        dej3        d ej3        d!ej3        dz  d"e6d#e6d$e%e*         fd%„Z7 ed&¦  «        d;d'„¦   «         Z8d(„ Z9 ee8¦  «         G d)„ d*ej1        ¦  «        ¦   «         Z: G d+„ d,ej1        ¦  «        Z; G d-„ d.e¦  «        Z< G d/„ d0ej1        ¦  «        Z=e' G d1„ d2e#¦  «        ¦   «         Z>e' G d3„ d4e>¦  «        ¦   «         Z?e' G d5„ d6e>e¦  «        ¦   «         Z@ G d7„ d8ee>¦  «        ZAg d9¢ZBdS )<é    )ÚCallable)ÚOptionalNé   )Úinitialization)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_forward_from_hubÚuse_kernel_func_from_hubÚuse_kernelized_func)Úcreate_causal_maskÚ!create_sliding_window_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TransformersKwargsÚmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputsé   )ÚOlmo3ConfigÚ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Olmo3RMSNormç�íµ ÷Æ°>ÚepsÚreturnNc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z;
        Olmo3RMSNorm 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/olmo3/modeling_olmo3.pyr)   zOlmo3RMSNorm.__init__.   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.   )r0   Úhidden_statesÚinput_dtypeÚvariances       r3   ÚforwardzOlmo3RMSNorm.forward6   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<r4   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)Útupler.   Úshaper/   )r0   s    r3   Ú
extra_reprzOlmo3RMSNorm.extra_repr=   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr4   )r$   )
Ú__name__Ú
__module__Ú__qualname__Úfloatr)   r,   ÚTensorrB   rF   Ú__classcell__©r2   s   @r3   r#   r#   ,   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r4   r#   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)rE   ÚexpandÚreshape)r?   rN   ÚbatchÚnum_key_value_headsÚslenÚhead_dims         r3   Ú	repeat_kvrV   A   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Tr4   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 )Nr6   r   r7   )Údimr9   )ÚpÚtrainingr   )rV   Únum_key_value_groupsr,   ÚmatmulÚ	transposer*   Ú
functionalÚsoftmaxr;   r:   r9   r^   rc   Ú
contiguous)rX   rY   rZ   r[   r\   r]   r^   r_   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r3   Úeager_attention_forwardrn   M   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$Ð$r4   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.
    )r9   Ú	unsqueezeÚrotate_halfr:   )	ÚqÚkÚcosÚsinÚunsqueeze_dimÚq_typeÚk_typeÚq_embedÚk_embeds	            r3   Úapply_rotary_pos_embr|   f   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1r4   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..Nr7   r6   ©ra   )rE   r,   Úcat)ÚxÚx1Úx2s      r3   rr   rr   �   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'r4   c                   óÊ   ‡ — e Zd ZdZdede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Olmo3Attentionz=Multi-headed attention from 'Attention Is All You Need' paperÚconfigÚ	layer_idxc                 ó   •— 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        ¦  «        | _        |j        |         | _        | j        dk    r|j        nd | _        d S )NrU   g      à¿T©ÚbiasÚsliding_attention)r(   r)   r…   r†   Úgetattrr1   Únum_attention_headsrU   rS   rd   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_normÚlayer_typesÚattention_typeÚsliding_window©r0   r…   r†   r2   s      €r3   r)   zOlmo3Attention.__init__Œ   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Ø$Ô0°Ô;ˆÔØ7;Ô7JÐNaÒ7aÐ7a˜fÔ3Ð3ÐgkˆÔÐÐr4   Nr?   Úposition_embeddingsr\   Úpast_key_valuesr_   r&   c                 ó†  — |j         d d…         }g |¢d‘| j        ‘R }|                      |                      |¦  «        ¦  «        }|                      |                      |¦  «        ¦  «        }	|                      |¦  «        }
|                     |¦  «                             dd¦  «        }|	                     |¦  «                             dd¦  «        }	|
                     |¦  «                             dd¦  «        }
|\  }}t          ||	||¦  «        \  }}	|�| 
                    |	|
| j        ¦  «        \  }	}
t          j        | j        j        t           ¦  «        } || ||	|
|f| j        sdn| j        | j        | j        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )Nr7   r   r6   rW   )r^   r]   rš   )rE   rU   r–   r‘   r—   r’   r“   Úviewrf   r|   Úupdater†   r   Úget_interfacer…   Ú_attn_implementationrn   rc   r�   r]   rš   rQ   ri   r”   )r0   r?   rœ   r\   r�   r_   Úinput_shapeÚhidden_shapeÚquery_statesrj   rk   ru   rv   Úattention_interfacerm   rl   s                   r3   rB   zOlmo3Attention.forward§   sè  € ð $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”LØÔ.ð
%
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(r4   ©N)rG   rH   rI   Ú__doc__r    Úintr)   r,   rK   rD   r   r   r   rB   rL   rM   s   @r3   r„   r„   ˆ   sæ   ø€ € € € € àGÐGðl˜{ð l°sð lð lð lð lð lð l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 +)r4   r„   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚOlmo3MLPc                 ó˜  •— t          ¦   «                              ¦   «          || _        |j        | _        |j        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _	        t          |j                 | _        d S ©NFrˆ   )r(   r)   r…   r1   Úintermediate_sizer*   r�   Ú	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©r0   r…   r2   s     €r3   r)   zOlmo3MLP.__init__Ö   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r4   c                 ó¨   — |                       |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        }|S r§   )r±   r³   r¯   r°   )r0   r€   r±   s      r3   rB   zOlmo3MLP.forwardà   sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr4   )rG   rH   rI   r)   rB   rL   rM   s   @r3   r«   r«   Õ   sG   ø€ € € € € ð0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð r4   r«   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Olmo3DecoderLayerr…   r†   c                 ó4  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        |j        ¬¦  «        | _	        t          |j        |j        ¬¦  «        | _
        d S )N)r…   r†   ©r%   )r(   r)   r1   r„   Ú	self_attnr«   Úmlpr#   r•   Úpost_attention_layernormÚpost_feedforward_layernormr›   s      €r3   r)   zOlmo3DecoderLayer.__init__æ   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'r4   NFr?   r\   Úposition_idsr�   Ú	use_cacherœ   r_   r&   c           
      óÎ   — |} | j         d||||||dœ|¤Ž\  }}	|                      |¦  «        }||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r?   r\   r¾   r�   r¿   rœ   © )rº   r¼   r»   r½   )
r0   r?   r\   r¾   r�   r¿   rœ   r_   ÚresidualÚ_s
             r3   rB   zOlmo3DecoderLayer.forwardï   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r4   )NNNFN)rG   rH   rI   r    r©   r)   r,   rK   Ú
LongTensorr   ÚboolrD   r   r   rB   rL   rM   s   @r3   r·   r·   å   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 r4   r·   c                   óâ   ‡ — 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z  d	ed
ef         f
d„¦   «         Z ej        ¦   «         edd„¦   «         ¦   «         Zˆ xZS )ÚOlmo3RotaryEmbeddingÚinv_freqNr…   c                 ó€  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        t          t          |j        ¦  «        ¦  «        | _        i | _	        | j        D ]È}| j        j
        |         }|€Œ|d         | j	        |<   | j        }| j	        |         dk    rt          | j	        |                  } || j        |¬¦  «        \  }}|                      |› d�|d¬¦  «         |                      |› d�|                     ¦   «         d¬¦  «         t          | |› d�|¦  «         ŒÉd S )	NÚ	rope_typeÚdefault©Ú
layer_typeÚ	_inv_freqF)Ú
persistentÚ_original_inv_freqÚ_attention_scaling)r(   r)   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr…   ÚlistÚsetr˜   rÊ   Úrope_parametersÚcompute_default_rope_parametersr   Úregister_bufferÚcloneÚsetattr)	r0   r…   ÚdevicerÍ   Úrope_paramsÚrope_init_fnÚcurr_inv_freqÚcurr_attention_scalingr2   s	           €r3   r)   zOlmo3RotaryEmbedding.__init__  s^  ø€ Ý‰Œ×ÒÑÔÐØ"(Ô"@ˆÔØ$*Ô$BˆÔ!ØˆŒÝ¥ FÔ$6Ñ 7Ô 7Ñ8Ô8ˆÔØˆŒØÔ*ð 	Uð 	UˆJØœ+Ô5°jÔAˆKØÐ"Øà)4°[Ô)AˆDŒN˜:Ñ&Ø%)Ô%IˆLØŒ~˜jÔ)¨YÒ6Ð6Ý2°4´>À*Ô3MÔN�Ø4@°LÀÄÐYcÐ4dÑ4dÔ4dÑ1ˆMÐ1Ø× Ò  JÐ!9Ð!9Ð!9¸=ÐUZÐ Ñ[Ô[Ð[Ø× Ò  JÐ!BÐ!BÐ!BÀM×DWÒDWÑDYÔDYÐfkÐ ÑlÔlÐlÝ�D˜ZÐ;Ð;Ð;Ð=SÑTÔTÐTÐTð	Uð 	Ur4   rÜ   ztorch.deviceÚseq_lenrÍ   r&   ztorch.Tensorc                 ó  — | 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.
            layer_type (`str`, *optional*):
                The current layer type if the model has different RoPE parameters per type.
                Should not be used unless `config.layer_types is not None`

        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_thetarU   Ng      ð?r   r6   )r9   )rÜ   r9   )	r×   r‹   r1   rŒ   r,   ÚarangeÚint64r:   rJ   )r…   rÜ   rá   rÍ   Úbasera   Úattention_factorrÈ   s           r3   rØ   z4Olmo3RotaryEmbedding.compute_default_rope_parameters&  s‘   € ð2 Ô% jÔ1°,Ô?ˆ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)r4   c                 ó  — t          | |› d�¦  «        }t          | |› d�¦  «        }|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¬¦  «        }
|
                     ¦   «         |z  }|
                     ¦   «         |z  }d d d ¦  «         n# 1 swxY w Y   ||fS )NrÎ   rÑ   r   r7   r   ÚmpsÚcpuF)Údevice_typeÚenabledr6   r~   )r‹   rJ   rP   rE   r:   rÜ   Ú
isinstanceÚtypeÚstrr   rf   r,   r   ru   rv   )r0   r€   r¾   rÍ   rÈ   Úattention_scalingÚinv_freq_expandedÚposition_ids_expandedrë   ÚfreqsÚembru   rv   s                r3   rB   zOlmo3RotaryEmbedding.forwardJ  sÀ  € õ ˜4 JÐ!9Ð!9Ð!9Ñ:Ô:ˆÝ# D¨ZÐ*KÐ*KÐ*KÑLÔLÐà$ T¨1¨1¨1¨d ]Ô3×9Ò9Ñ;Ô;×BÒBÀ<ÔCUÐVWÔCXÐZ\Ð^_Ñ`Ô`×cÒcÐdeÔdlÑmÔmÐ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 	0ð 	0Ø&×,Ò,Ñ.Ô.Ð1F×1LÒ1LÑ1NÔ1NÑN×YÒYÐZ[Ð]^Ñ_Ô_ˆEÝ”)˜U E˜N°Ð3Ñ3Ô3ˆCØ—'’'‘)”)Ð/Ñ/ˆCØ—'’'‘)”)Ð/Ñ/ˆCð		0ð 	0ð 	0ñ 	0ô 	0ð 	0ð 	0ð 	0ð 	0ð 	0ð 	0øøøð 	0ð 	0ð 	0ð 	0ð �Cˆxˆs   Ã-BE=Å=FÆFr§   )NNNN)rG   rH   rI   r,   rK   Ú__annotations__r    r)   Ústaticmethodr   r©   rï   rD   rJ   rØ   Úno_gradr   rB   rL   rM   s   @r3   rÇ   rÇ     s  ø€ € € € € € ØŒlÐÐÑðUð U˜{ð Uð Uð Uð Uð Uð Uð* à%)Ø+/Ø"Ø!%ð	!*ð !*Ø˜dÑ"ð!*à˜Ô(ð!*ð �t‘ð!*ð ˜$‘Jð	!*ð
 
ˆ~˜uÐ$Ô	%ð!*ð !*ð !*ñ „\ð!*ðF €U„]�_„_Øðð ð ñ Ôñ „_ðð ð ð ð r4   rÇ   c                   ó\   ‡ — 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ˆ fd„Zˆ xZS )ÚOlmo3PreTrainedModelr…   ÚmodelTr·   r�   )r?   Ú
attentionsc                 ó®  •— t          ¦   «                              |¦  «         t          |t          ¦  «        r›|j        D ]•}|j        }|j        |         dk    rt          |j        |                  } ||j        |¬¦  «        \  }}t          j
        t          ||› d�¦  «        |¦  «         t          j
        t          ||› d�¦  «        |¦  «         Œ”d S d S )NrË   rÌ   rÎ   rÐ   )r(   Ú_init_weightsrí   rÇ   r˜   rØ   rÊ   r   r…   ÚinitÚcopy_r‹   )r0   rX   rÍ   rÞ   rß   rÃ   r2   s         €r3   rý   z"Olmo3PreTrainedModel._init_weightsp  sð   ø€ Ý‰Œ×Ò˜fÑ%Ô%Ð%Ý�fÕ2Ñ3Ô3ð 	^Ø$Ô0ð ^ð ^�
Ø%ÔE�ØÔ# JÔ/°9Ò<Ð<Ý#6°vÔ7GÈ
Ô7SÔ#T�LØ#/ <°´È*Ð#UÑ#UÔ#UÑ �˜qÝ”
�7 6¨jÐ+CÐ+CÐ+CÑDÔDÀmÑTÔTÐTÝ”
�7 6¨jÐ+LÐ+LÐ+LÑMÔMÈ}Ñ]Ô]Ð]Ð]ð	^ð 	^ð^ð ^r4   )rG   rH   rI   r    rõ   Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendr·   r„   Ú_can_record_outputsrý   rL   rM   s   @r3   rù   rù   ^  s�   ø€ € € € € € àÐÐÑØÐØ&*Ð#Ø,Ð-ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà*Ø$ðð Ðð
	^ð 	^ð 	^ð 	^ð 	^ð 	^ð 	^ð 	^ð 	^r4   rù   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
Olmo3Modelr…   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 rÁ   )r·   )Ú.0r†   r…   s     €r3   ú
<listcomp>z'Olmo3Model.__init__.<locals>.<listcomp>…  s$   ø€ ÐcÐcÐc°iÕ˜v yÑ1Ô1ÐcÐcÐcr4   r¹   ©r…   F)r(   r)   Úpad_token_idÚpadding_idxÚ
vocab_sizer*   Ú	Embeddingr1   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr#   r•   ÚnormrÇ   Ú
rotary_embÚgradient_checkpointingÚ	post_initr´   s    `€r3   r)   zOlmo3Model.__init__~  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r4   NÚ	input_idsr\   r¾   r�   Úinputs_embedsr¿   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          |x}	t          ¦  «        s&| j        ||||dœ}
t          d
i |
¤Žt          d
i |
¤Ždœ}	|}i }t          | j        j        ¦  «        D ]}|                      |||¦  «        ||<   Œt#          | j        d | j        j        …         ¦  «        D ]?\  }} ||f|	| j        j        |                  |||| j        j        |                  dœ|¤Ž}Œ@|                      |¦  «        }t+          ||¬	¦  «        S )Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )rÜ   )r…   r  r\   r�   r¾   )Úfull_attentionrŠ   )r\   r¾   r�   rœ   )Úlast_hidden_stater�   rÁ   )Ú
ValueErrorr  r	   r…   Úget_seq_lengthr,   rä   rE   rÜ   rq   rí   Údictr   r   rÖ   r˜   r  Ú	enumerater  r  r  r   )r0   r  r\   r¾   r�   r  r¿   r_   Úpast_seen_tokensÚcausal_mask_mappingÚmask_kwargsr?   rœ   rÍ   ÚiÚdecoder_layers                   r3   rB   zOlmo3Model.forwardŽ  s%  € 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4ˆLõ °Ð?Ð-ÅÑFÔFð 	ð œ+Ø!.Ø"0Ø#2Ø ,ðð ˆKõ #5Ð"CÐ"C°{Ð"CÐ"CÝ%FÐ%UÐ%UÈÐ%UÐ%Uð#ð #Ðð
 &ˆØ ÐÝ˜dœkÔ5Ñ6Ô6ð 	gð 	gˆJØ.2¯oªo¸mÈ\Ð[eÑ.fÔ.fÐ 
Ñ+Ð+å )¨$¬+Ð6U¸¼Ô8UÐ6UÔ*VÑ WÔ Wð 	ð 	ÑˆAˆ}Ø)˜MØðà2°4´;Ô3JÈ1Ô3MÔNØ)Ø /Ø$7¸¼Ô8OÐPQÔ8RÔ$Sðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝ&Ø+Ø+ð
ñ 
ô 
ð 	
r4   )NNNNNN)rG   rH   rI   r    r)   r   r   r   r,   rÄ   rK   r   ÚFloatTensorrÅ   r   r   r   rB   rL   rM   s   @r3   r  r  |  s  ø€ € € € € ð˜{ð ð ð ð ð ð ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð;
ð ;
àÔ# dÑ*ð;
ð œ tÑ+ð;
ð Ô&¨Ñ-ð	;
ð
  ™ð;
ð Ô(¨4Ñ/ð;
ð ˜$‘;ð;
ð Ð+Ô,ð;
ð 
!ð;
ð ;
ð ;
ñ „^ñ „_ñ  Ôð;
ð ;
ð ;
ð ;
ð ;
r4   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Olmo3ForCausalLMz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 r­   )
r(   r)   r  rú   r  r*   r�   r1   r/  r  r´   s     €r3   r)   zOlmo3ForCausalLM.__init__Õ  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r4   Nr   r  r\   r¾   r�   r  Úlabelsr¿   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, Olmo3ForCausalLM

        >>> model = Olmo3ForCausalLM.from_pretrained("meta-olmo3/Olmo3-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-olmo3/Olmo3-2-7b-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\   r¾   r�   r  r¿   N)r1  r3  r  )Úlossr1  r�   r?   rû   rÁ   )rú   r"  rí   r©   Úslicer/  Úloss_functionr…   r  r   r�   r?   rû   )r0   r  r\   r¾   r�   r  r3  r¿   r4  r_   Úoutputsr?   Úslice_indicesr1  r6  s                  r3   rB   zOlmo3ForCausalLM.forwardÞ  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 	
r4   )NNNNNNNr   )rG   rH   rI   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr)   r   r   r,   rÄ   rK   r   r,  rÅ   r©   r   r   r   rB   rL   rM   s   @r3   r.  r.  Ï  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 ˜$‘;ð6
ð ˜eœlÑ*ð6
ð Ð+Ô,ð6
ð 
 ð6
ð 6
ð 6
ñ „^ñ Ôð6
ð 6
ð 6
ð 6
ð 6
r4   r.  c                   ó   — e Zd ZdS )ÚOlmo3ForSequenceClassificationN)rG   rH   rI   rÁ   r4   r3   r?  r?    s   € € € € € Ø€Dr4   r?  )r.  r?  r  rù   )rW   )r   )CÚcollections.abcr   Útypingr   r,   Útorch.nnr*   Ú r   rþ   Úactivationsr   Úcache_utilsr   r	   Ú
generationr
   Úintegrationsr   r   r   Úmasking_utilsr   r   Úmodeling_layersr   r   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   Úutils.genericr   r   r   Úutils.output_capturingr   Úconfiguration_olmo3r    ÚModuler#   rK   r©   rV   rJ   rn   r|   rr   r„   r«   r·   rÇ   rù   r  r.  r?  Ú__all__rÁ   r4   r3   ú<module>rT     s¬  ðð* %Ð $Ð $Ð $Ð $Ð $Ø Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð à &Ð &Ð &Ð &Ð &Ð &Ø !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 RÐ RÐ RÐ RÐ RÐ RÐ RÐ RØ [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 [Ð [Ð [Ð [Ð [Ð [Ð [Ð [Ð [Ð [Ø 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(	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I)ð I)ð I)ð I)ð I)�R”Yñ I)ô I)ñ +Ô*ðI)ðXð ð ð ð ˆrŒyñ ô ð ð &ð &ð &ð &ð &Ð2ñ &ô &ð &ðRMð Mð Mð Mð M˜2œ9ñ Mô Mð Mð` ð^ð ^ð ^ð ^ð ^˜?ñ ^ô ^ñ „ð^ð: ðO
ð O
ð O
ð O
ð O
Ð%ñ O
ô O
ñ „ðO
ðd 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€€€r4   