§
    ‚ŠtjoS  ã                   óZ  — d dl mZ d dlmZ d dlZd dlmZ d dlmc 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 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$m%Z%m&Z&m'Z' ddl(m)Z)m*Z* ddl+m,Z, ddl-m.Z.  G d„ dej/        ¦  «        Z0 G d„ dej/        ¦  «        Z1 G d„ dej/        ¦  «        Z2d„ Z3dej4        de5dej4        fd„Z6	 d8d ej/        d!ej4        d"ej4        d#ej4        d$ej4        dz  d%e7d&e7d'e#e%         fd(„Z8 ed)¦  «        d9d*„¦   «         Z9 ee9¦  «         G d+„ d,ej/        ¦  «        ¦   «         Z: G d-„ d.e¦  «        Z;e& G d/„ d0e!¦  «        ¦   «         Z<e& G d1„ d2e<¦  «        ¦   «         Z=e& G d3„ d4e<e¦  «        ¦   «         Z> G d5„ d6ee<¦  «        Z?g d7¢Z@dS ):é    )ÚCallable)ÚOptionalNé   )ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Ú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TransformersKwargsÚauto_docstringÚcan_return_tuple)Úmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputsé   )Ú
OlmoConfigc                   óP   ‡ — e Zd ZdZdeddfˆ fd„Zdej        dej        fd„Zˆ xZ	S )ÚOlmoLayerNormz/LayerNorm but with no learnable weight or bias.Úhidden_sizeÚreturnNc                 óX   •— t          ¦   «                              ¦   «          |f| _        d S ©N)ÚsuperÚ__init__Únormalized_shape)Úselfr    Ú	__class__s     €úd/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/olmo/modeling_olmo.pyr%   zOlmoLayerNorm.__init__4   s)   ø€ Ý‰Œ×ÒÑÔÐØ!, ˆÔÐÐó    Úhidden_statesc                 ó®   — |j         }t          j        |                     t          j        ¬¦  «        | j        d d d¬¦  «                             |¦  «        S )N©Údtypegñhãˆµøä>)Úeps)r.   ÚFÚ
layer_normÚtoÚtorchÚfloat32r&   )r'   r+   Ú
orig_dtypes      r)   ÚforwardzOlmoLayerNorm.forward8   sS   € Ø"Ô(ˆ
ÝŒ|˜M×,Ò,µ5´=Ð,ÑAÔAÀ4ÔCXÐZ^Ð`dÐjnÐoÑoÔo×rÒrØñ
ô 
ð 	
r*   )
Ú__name__Ú
__module__Ú__qualname__Ú__doc__Úintr%   r3   ÚTensorr6   Ú__classcell__©r(   s   @r)   r   r   1   sw   ø€ € € € € Ø9Ð9ð/ Cð /¨Dð /ð /ð /ð /ð /ð /ð
 U¤\ð 
°e´lð 
ð 
ð 
ð 
ð 
ð 
ð 
ð 
r*   r   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚOlmoMLPc                 ó˜  •— t          ¦   «                              ¦   «          || _        |j        | _        |j        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _	        t          |j                 | _        d S ©NF©Úbias)r$   r%   Úconfigr    Úintermediate_sizeÚnnÚLinearÚ	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©r'   rE   r(   s     €r)   r%   zOlmoMLP.__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 r#   )rK   rM   rI   rJ   )r'   ÚxrK   s      r)   r6   zOlmoMLP.forwardJ   sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr*   )r7   r8   r9   r%   r6   r=   r>   s   @r)   r@   r@   ?   sG   ø€ € € € € ð0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð r*   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OlmoRotaryEmbeddingÚinv_freqNrE   c                 ó²  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        | j        j        d         | _        | j        }| j        dk    rt          | j                 } || j        |¦  «        \  }| _
        |                      d|d¬¦  «         |                      d|                     ¦   «         d¬¦  «         d S )NÚ	rope_typeÚdefaultrS   F)Ú
persistentÚoriginal_inv_freq)r$   r%   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrE   Úrope_parametersrU   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r'   rE   ÚdeviceÚrope_init_fnrS   r(   s        €r)   r%   zOlmoRotaryEmbedding.__init__R   sÊ   ø€ Ý‰Œ×ÒÑÔÐØ"(Ô"@ˆÔØ$*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Ur*   ra   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   é   r-   )ra   r.   )	r\   Úgetattrr    Únum_attention_headsr3   ÚarangeÚint64r2   Úfloat)rE   ra   rc   ÚbaseÚdimÚattention_factorrS   s          r)   r]   z3OlmoRotaryEmbedding.compute_default_rope_parametersb   sŒ   € ð& Ô% lÔ3ˆÝ�f˜j¨$Ñ/Ô/Ðc°6Ô3EÈÔIcÑ3cˆàÐð Ø•U”\ ! S¨!µ5´;Ð?Ñ?Ô?×BÒBÈ&ÕX]ÔXcÐBÑdÔdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r*   c                 óê  — | j         d d d …d f                              ¦   «                              |j        d         dd¦  «                             |j        ¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  |                     ¦   «         |                     ¦   «         z   
                    dd¦  «        }t          j        ||fd¬	¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   ||	fS )
Nr   éÿÿÿÿr   ÚmpsÚcpuF)Údevice_typeÚenabledrg   ©rn   )rS   rl   ÚexpandÚshaper2   ra   Ú
isinstanceÚtypeÚstrr   Ú	transposer3   ÚcatÚcosr^   Úsin)
r'   rP   Úposition_idsÚinv_freq_expandedÚposition_ids_expandedrt   ÚfreqsÚembr~   r   s
             r)   r6   zOlmoRotaryEmbedding.forward€   s•  € ð !œM¨$°°°°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*r#   )NNN)r7   r8   r9   r3   r<   Ú__annotations__r   r%   Ústaticmethodr   r;   Útuplerl   r]   Úno_gradr   r6   r=   r>   s   @r)   rR   rR   O   sù   ø€ € € € € € ØŒlÐÐÑðVð V˜zð Vð Vð Vð Vð Vð Vð  à$(Ø+/Ø"ð*ð *Ø˜TÑ!ð*à˜Ô(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ô	%ð	*ð *ð *ñ „\ð*ð: €U„]�_„_Øð
ð 
ñ Ôñ „_ð
ð 
ð 
ð 
ð 
r*   rR   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..Nrq   rg   rv   )rx   r3   r}   )rP   Úx1Úx2s      r)   Úrotate_halfrŒ   �   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'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)rx   rw   Úreshape)r+   r�   ÚbatchÚnum_key_value_headsÚslenrf   s         r)   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Tr*   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 )Nrg   r   rq   )rn   r.   )ÚpÚtrainingr   )r“   Únum_key_value_groupsr3   Úmatmulr|   rG   Ú
functionalÚsoftmaxr4   r2   r.   r›   rŸ   Ú
contiguous)r•   r–   r—   r˜   r™   rš   r›   rœ   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*   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.
    )r.   Ú	unsqueezerŒ   r2   )	ÚqÚkr~   r   Úunsqueeze_dimÚq_typeÚk_typeÚq_embedÚk_embeds	            r)   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1r*   c                   óº   ‡ — 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j        ej        dz  f         f
d„Zˆ xZS )ÚOlmoAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrE   Ú	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        ¬¦  «        | _        d S )Nrf   g      à¿TrC   )r$   r%   rE   r·   rh   r    ri   rf   r‘   r    rš   Úattention_dropoutÚ	is_causalrG   rH   Úattention_biasÚq_projÚk_projÚv_projÚo_proj©r'   rE   r·   r(   s      €r)   r%   zOlmoAttention.__init__Ú   sB  ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒÝ ¨
°FÔ4FÈ&ÔJdÑ4dÑeÔeˆŒØ$*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ˆˆr*   Nr+   Úposition_embeddingsr™   Úpast_key_valuesr!   c                 óN  — |j         d d…         }g |¢d‘| j        ‘R }|                      |¦  «        }|                      |¦  «        }	|                      |¦  «        }
| j        j        �„|                     | j        j         | j        j        ¬¦  «         |	                     | j        j         | j        j        ¬¦  «         |
                     | j        j         | j        j        ¬¦  «         |                     |¦  «         	                    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 )Nrq   )ÚminÚmaxr   rg   r”   )r›   rš   )rx   rf   r¼   r½   r¾   rE   Úclip_qkvÚclamp_Úviewr|   r´   Úupdater·   r   Úget_interfaceÚ_attn_implementationr©   rŸ   r¹   rš   r�   r¤   r¿   )r'   r+   rÁ   r™   rÂ   rœ   Úinput_shapeÚhidden_shapeÚquery_statesr¥   r¦   r~   r   Úattention_interfacer¨   r§   s                   r)   r6   zOlmoAttention.forwardñ   sG  € ð $Ô)¨#¨2¨#Ô.ˆØ8˜Ð8 bÐ8¨$¬-Ð8Ð8ˆà—{’{ =Ñ1Ô1ˆØ—[’[ Ñ/Ô/ˆ
Ø—{’{ =Ñ1Ô1ˆàŒ;ÔÐ+Ø×Ò T¤[Ô%9Ð$9¸t¼{Ô?SÐÑTÔTÐTØ×Ò 4¤;Ô#7Ð"7¸T¼[Ô=QÐÑRÔRÐRØ×Ò T¤[Ô%9Ð$9¸t¼{Ô?SÐÑTÔTÐTà#×(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(r*   r#   )r7   r8   r9   r:   r   r;   r%   r3   r<   r‡   r   r6   r=   r>   s   @r)   r¶   r¶   Ö   sÍ   ø€ € € € € àGÐGð
˜zð 
°cð 
ð 
ð 
ð 
ð 
ð 
ð8 )-ð/)ð /)à”|ð/)ð # 5¤<°´Ð#=Ô>ð/)ð œ tÑ+ð	/)ð
  ™ð/)ð 
ˆuŒ|˜Uœ\¨DÑ0Ð0Ô	1ð/)ð /)ð /)ð /)ð /)ð /)ð /)ð /)r*   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OlmoDecoderLayerrE   r·   c                 ó  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        ¦  «        | _        t          |j        ¦  «        | _	        d S )N)rE   r·   )
r$   r%   r    r¶   Ú	self_attnr@   Úmlpr   Úinput_layernormÚpost_attention_layernormrÀ   s      €r)   r%   zOlmoDecoderLayer.__init__$  sq   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔÝ&¨fÀ	ÐJÑJÔJˆŒå˜6‘?”?ˆŒÝ,¨VÔ-?Ñ@Ô@ˆÔÝ(5°fÔ6HÑ(IÔ(IˆÔ%Ð%Ð%r*   NFr+   r™   r€   rÂ   Ú	use_cacherÁ   rœ   r!   c           
      óÎ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r+   r™   r€   rÂ   r×   rÁ   © )rÕ   rÓ   rÖ   rÔ   )
r'   r+   r™   r€   rÂ   r×   rÁ   rœ   ÚresidualÚ_s
             r)   r6   zOlmoDecoderLayer.forward-  s¡   € ð !ˆØ×,Ò,¨]Ñ;Ô;ˆà)˜4œ>ð 
Ø'Ø)Ø%Ø+ØØ 3ð
ð 
ð ð
ð 
Ñˆ�qð ! =Ñ0ˆð !ˆØ×5Ò5°mÑDÔDˆØŸš Ñ/Ô/ˆØ  =Ñ0ˆØÐr*   )NNNFN)r7   r8   r9   r   r;   r%   r3   r<   Ú
LongTensorr   Úboolr‡   r   r   r6   r=   r>   s   @r)   rÑ   rÑ   #  sÿ   ø€ € € € € ðJ˜zð J°cð Jð Jð Jð Jð Jð Jð /3Ø04Ø(,Ø!&ØHLðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r*   rÑ   c                   óL   — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZdS )ÚOlmoPreTrainedModelrE   ÚmodelTrÑ   rÂ   )r+   Ú
attentionsN)r7   r8   r9   r   r…   Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendrÑ   r¶   Ú_can_record_outputsrÙ   r*   r)   rß   rß   M  sl   € € € € € € àÐÐÑØÐØ&*Ð#Ø+Ð,ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà)Ø#ðð ÐÐÐr*   rß   c                   óâ   ‡ — e Zd Zdefˆ fd„Zeee	 	 	 	 	 	 ddej	        dz  dej
        dz  dej	        dz  dedz  dej        dz  d	edz  d
ee         defd„¦   «         ¦   «         ¦   «         Zˆ xZS )Ú	OlmoModelrE   c                 óÐ  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ¦  «        | _        t          ‰¬¦  «        | _        d| _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS rÙ   )rÑ   )Ú.0r·   rE   s     €r)   ú
<listcomp>z&OlmoModel.__init__.<locals>.<listcomp>i  s$   ø€ ÐbÐbÐb°YÕ˜f iÑ0Ô0ÐbÐbÐbr*   ©rE   F)r$   r%   Úpad_token_idÚpadding_idxÚ
vocab_sizerG   Ú	Embeddingr    Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr   ÚnormrR   Ú
rotary_embÚgradient_checkpointingÚ	post_initrN   s    `€r)   r%   zOlmoModel.__init__b  sÌ   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØbÐbÐbÐbÅ%ÈÔH`ÑBaÔBaÐbÑbÔbñ
ô 
ˆŒõ " &Ô"4Ñ5Ô5ˆŒ	Ý-°VÐ<Ñ<Ô<ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr*   NÚ	input_idsr™   r€   rÂ   Úinputs_embedsr×   rœ   r!   c           
      óH  — |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }t          | j        ||||¬¦  «        }	|}
|                      |
|¬¦  «        }| j        d | j        j        …         D ]} ||
f|	||||dœ|¤Ž}
Œ|                      |
¦  «        }
t          |
|¬	¦  «        S )
Nz:You must specify exactly one of input_ids or inputs_embedsrò   r   r   )ra   )rE   r  r™   rÂ   r€   )r€   )r™   rÁ   r€   rÂ   r×   )Úlast_hidden_staterÂ   )Ú
ValueErrorr÷   r   rE   Úget_seq_lengthr3   rj   rx   ra   r¬   r   rý   rû   rú   rü   r   )r'   r   r™   r€   rÂ   r  r×   rœ   Úpast_seen_tokensÚcausal_maskr+   rÁ   Údecoder_layers                r)   r6   zOlmoModel.forwardr  sŠ  € ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàÐ Ø*.×*;Ò*;¸IÑ*FÔ*FˆMàð 	?˜Ð0Ý*°$´+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$7Ø)Ø /Ø#ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝ&Ø+Ø+ð
ñ 
ô 
ð 	
r*   )NNNNNN)r7   r8   r9   r   r%   r   r   r   r3   rÜ   r<   r   ÚFloatTensorrÝ   r   r   r   r6   r=   r>   s   @r)   rí   rí   `  s  ø€ € € € € ð˜zð ð ð ð ð ð ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð2
ð 2
àÔ# dÑ*ð2
ð œ tÑ+ð2
ð Ô&¨Ñ-ð	2
ð
  ™ð2
ð Ô(¨4Ñ/ð2
ð ˜$‘;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*   rí   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OlmoForCausalLMz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 rB   )
r$   r%   rí   rà   rõ   rG   rH   r    r  rÿ   rN   s     €r)   r%   zOlmoForCausalLM.__init__°  sj   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ý˜vÑ&Ô&ˆŒ
Ø Ô+ˆŒÝ”y Ô!3°VÔ5FÈUÐSÑSÔSˆŒð 	�ŠÑÔÐÐÐr*   Nr   r   r™   r€   rÂ   r  Úlabelsr×   Úlogits_to_keeprœ   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 )aÉ  
        Example:

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

        >>> model = OlmoForCausalLM.from_pretrained("meta-olmo/Olmo-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-olmo/Olmo-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™   r€   rÂ   r  r×   N)r  r  rõ   )Úlossr  rÂ   r+   rá   rÙ   )rà   r  ry   r;   Úslicer  Úloss_functionrE   rõ   r   rÂ   r+   rá   )r'   r   r™   r€   rÂ   r  r  r×   r  rœ   Úoutputsr+   Úslice_indicesr  r  s                  r)   r6   zOlmoForCausalLM.forward¹  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 	
r*   )NNNNNNNr   )r7   r8   r9   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr%   r   r   r3   rÜ   r<   r   r	  rÝ   r;   r   r   r   r6   r=   r>   s   @r)   r  r  ª  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 ˜$‘;ð6
ð ˜eœlÑ*ð6
ð Ð+Ô,ð6
ð 
 ð6
ð 6
ð 6
ñ „^ñ Ôð6
ð 6
ð 6
ð 6
ð 6
r*   r  c                   ó   — e Zd ZdS )ÚOlmoForSequenceClassificationN)r7   r8   r9   rÙ   r*   r)   r  r  ô  s   € € € € € Ø€Dr*   r  )r  r  rí   rß   )r”   )r   )AÚcollections.abcr   Útypingr   r3   Útorch.nnrG   Útorch.nn.functionalr¢   r0   Úactivationsr   Úcache_utilsr   r   Ú
generationr	   Úintegrationsr
   r   Úmasking_utilsr   Úmodeling_layersr   r   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_olmor   ÚModuler   r@   rR   rŒ   r<   r;   r“   rl   r©   r´   r¶   rÑ   rß   rí   r  r  Ú__all__rÙ   r*   r)   ú<module>r1     sy  ðð4 %Ð $Ð $Ð $Ð $Ð $Ø Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð Ø Ð Ð Ð 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 IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ /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 IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ 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ð ð ð ð ˆbŒiñ ô ð ð =ð =ð =ð =ð =˜"œ)ñ =ô =ð =ð@(ð (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)Ñ*Ô*ðI)ð I)ð I)ð I)ð I)�B”Iñ I)ô I)ñ +Ô*ðI)ðX'ð 'ð 'ð 'ð 'Ð1ñ 'ô 'ð 'ðT ðð ð ð ð ˜/ñ ô ñ „ðð$ ðF
ð F
ð F
ð F
ð F
Ð#ñ F
ô F
ñ „ðF
ðR ðF
ð F
ð F
ð F
ð F
Ð)¨?ñ F
ô F
ñ „ðF
ðR	ð 	ð 	ð 	ð 	Ð$DÐFYñ 	ô 	ð 	ð cÐ
bÐ
b€€€r*   