§
    ‚ŠtjÀW  ã                   óœ  — 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 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# ddl$m%Z%m&Z&m'Z' ddl(m)Z)m*Z* ddl+m,Z, ddl-m.Z.  G d„ dej/        ¦  «        Z0 G d„ dej1        ¦  «        Z2 G d„ dej1        ¦  «        Z3 G d„ dej1        ¦  «        Z4d„ Z5 ed¦  «        d>d „¦   «         Z6d!ej7        d"e8d#ej7        fd$„Z9	 d?d&ej1        d'ej7        d(ej7        d)ej7        d*ej7        dz  d+e:d,e:d-e#e%         fd.„Z; ee6¦  «         G d/„ d0ej1        ¦  «        ¦   «         Z< G d1„ d2e¦  «        Z=e& G d3„ d4e!¦  «        ¦   «         Z>e& G d5„ d6e>¦  «        ¦   «         Z?e& G d7„ d8e>e¦  «        ¦   «         Z@ G d9„ d:ee>¦  «        ZA G d;„ d<ee>¦  «        ZBg d=¢ZCdS )@é    )ÚCallable)ÚOptionalN)Únné   )Úinitialization)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_func_from_hubÚuse_kernelized_func)Úcreate_causal_mask)Ú GenericForSequenceClassificationÚGenericForTokenClassificationÚ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GemmaConfigc            	       óP   ‡ — e Zd ZdZd
dedededefˆ fd„Zdej        fˆ fd	„Z	ˆ xZ
S )ÚGemmaTextScaledWordEmbeddingz\
    This module overrides nn.Embeddings' forward by multiplying with embeddings scale.
    ç      ð?Únum_embeddingsÚembedding_dimÚpadding_idxÚembed_scalec                 ó°   •— t          ¦   «                              |||¦  «         || _        |                      dt	          j        |¦  «        d¬¦  «         d S )Nr'   F©Ú
persistent)ÚsuperÚ__init__Úscalar_embed_scaleÚregister_bufferÚtorchÚtensor)Úselfr$   r%   r&   r'   Ú	__class__s        €úf/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/gemma/modeling_gemma.pyr,   z%GemmaTextScaledWordEmbedding.__init__7   sS   ø€ Ý‰Œ×Ò˜¨¸ÑDÔDÐDØ"-ˆÔØ×Ò˜]­E¬L¸Ñ,EÔ,EÐRWÐÑXÔXÐXÐXÐXó    Ú	input_idsc                 ó�   •— t          ¦   «                              |¦  «        | j                             | j        j        ¦  «        z  S ©N)r+   Úforwardr'   ÚtoÚweightÚdtype)r1   r5   r2   s     €r3   r8   z$GemmaTextScaledWordEmbedding.forward<   s4   ø€ Ý‰wŒw�Š˜yÑ)Ô)¨DÔ,<×,?Ò,?ÀÄÔ@QÑ,RÔ,RÑRÐRr4   )r#   )Ú__name__Ú
__module__Ú__qualname__Ú__doc__ÚintÚfloatr,   r/   ÚTensorr8   Ú__classcell__©r2   s   @r3   r"   r"   2   s¦   ø€ € € € € ðð ðYð Y sð Y¸3ð YÈSð YÐ_dð Yð Yð Yð Yð Yð Yð
S ¤ð Sð Sð Sð Sð Sð Sð Sð Sð Sð Sr4   r"   c                   ó<   ‡ — e Zd Zddedefˆ fd„Zd„ Zd„ Zd„ Zˆ xZ	S )	ÚGemmaRMSNormç�íµ ÷Æ°>ÚdimÚepsc                 ó¬   •— t          ¦   «                              ¦   «          || _        t          j        t          j        |¦  «        ¦  «        | _        d S r7   )r+   r,   rI   r   Ú	Parameterr/   Úzerosr:   )r1   rH   rI   r2   s      €r3   r,   zGemmaRMSNorm.__init__A   s?   ø€ Ý‰Œ×ÒÑÔÐØˆŒÝ”l¥5¤;¨sÑ#3Ô#3Ñ4Ô4ˆŒˆˆr4   c                 ó�   — |t          j        |                     d¦  «                             dd¬¦  «        | j        z   ¦  «        z  S )Né   éÿÿÿÿT)Úkeepdim)r/   ÚrsqrtÚpowÚmeanrI   )r1   Úxs     r3   Ú_normzGemmaRMSNorm._normF   s8   € Ø•5”;˜qŸušu Q™xœxŸ}š}¨R¸˜}Ñ>Ô>ÀÄÑIÑJÔJÑJÐJr4   c                 ó¸   — |                       |                     ¦   «         ¦  «        }|d| j                             ¦   «         z   z  }|                     |¦  «        S )Nr#   )rU   rA   r:   Útype_as)r1   rT   Úoutputs      r3   r8   zGemmaRMSNorm.forwardI   sL   € Ø—’˜AŸGšG™IœIÑ&Ô&ˆð ˜3 ¤×!2Ò!2Ñ!4Ô!4Ñ4Ñ5ˆØ�~Š~˜aÑ Ô Ð r4   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)Útupler:   ÚshaperI   )r1   s    r3   Ú
extra_reprzGemmaRMSNorm.extra_reprP   s%   € Ý˜œÔ)Ñ*Ô*Ð<Ð<°$´(Ð<Ð<Ð<r4   )rG   )
r<   r=   r>   r@   rA   r,   rU   r8   r\   rC   rD   s   @r3   rF   rF   @   s€   ø€ € € € € ð5ð 5˜Cð 5 eð 5ð 5ð 5ð 5ð 5ð 5ð
Kð Kð Kð!ð !ð !ð=ð =ð =ð =ð =ð =ð =r4   rF   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚGemmaMLPc                 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configÚhidden_sizeÚintermediate_sizer   ÚLinearÚ	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©r1   rc   r2   s     €r3   r,   zGemmaMLP.__init__U   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 r7   )ri   rk   rg   rh   )r1   rT   ri   s      r3   r8   zGemmaMLP.forward_   sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr4   )r<   r=   r>   r,   r8   rC   rD   s   @r3   r^   r^   T   sG   ø€ € € € € ð0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð r4   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GemmaRotaryEmbeddingÚinv_freqNrc   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defaultrp   Fr)   Úoriginal_inv_freq)r+   r,   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrc   Úrope_parametersrr   Úcompute_default_rope_parametersr   Úattention_scalingr.   Úclone)r1   rc   ÚdeviceÚrope_init_fnrp   r2   s        €r3   r,   zGemmaRotaryEmbedding.__init__g   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�$Ô(à×Ò˜Z¨¸eÐÑDÔDÐDØ×ÒÐ0°(·.².Ñ2BÔ2BÈuÐÑUÔUÐUÐUÐUr4   r|   ztorch.deviceÚseq_lenÚreturnztorch.Tensorc                 óü   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «                             |t          j        ¬¦  «        |z  z  z  }||fS )	a¨  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetaÚhead_dimNr#   r   rN   ©r;   )r|   r;   )	rx   Úgetattrrd   Únum_attention_headsr/   ÚarangeÚint64r9   rA   )rc   r|   r~   ÚbaserH   Úattention_factorrp   s          r3   ry   z4GemmaRotaryEmbedding.compute_default_rope_parametersw   sŒ   € ð& Ô% lÔ3ˆÝ�f˜j¨$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)r4   c                 óN  — | 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   |                     |j        ¬
¦  «        |	                     |j        ¬
¦  «        fS )Nr   rO   r   ÚmpsÚcpuF)Údevice_typeÚenabledrN   ©rH   rƒ   )rp   rA   Úexpandr[   r9   r|   Ú
isinstanceÚtypeÚstrr   Ú	transposer/   ÚcatÚcosrz   Úsinr;   )
r1   rT   Úposition_idsÚinv_freq_expandedÚposition_ids_expandedr�   ÚfreqsÚembr–   r—   s
             r3   r8   zGemmaRotaryEmbedding.forward•   s·  € ð !œM¨$°°°°4¨-Ô8×>Ò>Ñ@Ô@×GÒGÈÔHZÐ[\ÔH]Ð_aÐcdÑeÔe×hÒhÐijÔiqÑrÔrÐØ ,¨Q¨Q¨Q°°a°a°a¨ZÔ 8× >Ò >Ñ @Ô @Ðå'1°!´(´-ÅÑ'EÔ'EÐkÈ!Ì(Ì-Ð[`ÒJ`ÐJ`�a”h”m�mÐfkˆÝ¨¸UÐCÑCÔCð 	5ð 	5Ø&×,Ò,Ñ.Ô.Ð1F×1LÒ1LÑ1NÔ1NÑN×YÒYÐZ[Ð]^Ñ_Ô_ˆEÝ”)˜U E˜N°Ð3Ñ3Ô3ˆCØ—'’'‘)”)˜dÔ4Ñ4ˆCØ—'’'‘)”)˜dÔ4Ñ4ˆCð		5ð 	5ð 	5ñ 	5ô 	5ð 	5ð 	5ð 	5ð 	5ð 	5ð 	5øøøð 	5ð 	5ð 	5ð 	5ð �vŠv˜AœGˆvÑ$Ô$ c§f¢f°1´7 fÑ&;Ô&;Ð;Ð;s   ÃBE&Å&E*Å-E*r7   ©NNN)r<   r=   r>   r/   rB   Ú__annotations__r    r,   Ústaticmethodr   r@   rZ   rA   ry   Úno_gradr   r8   rC   rD   s   @r3   ro   ro   d   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 <r4   ro   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..NrO   rN   r�   )r[   r/   r•   )rT   Úx1Úx2s      r3   Úrotate_halfr¤   ¥   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   Úrotary_pos_embc                 ó¾   — |                      |¦  «        }|                      |¦  «        }| |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.
    )Ú	unsqueezer¤   )ÚqÚkr–   r—   Úunsqueeze_dimÚq_embedÚk_embeds          r3   Úapply_rotary_pos_embr­   ¬   sc   € ð& �-Š-˜Ñ
&Ô
&€CØ
�-Š-˜Ñ
&Ô
&€CØ�3‰w�; q™>œ>¨CÑ/Ñ0€GØ�3‰w�; q™>œ>¨CÑ/Ñ0€GØ�GÐÐr4   Úhidden_statesÚ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)r[   r�   Úreshape)r®   r¯   ÚbatchÚnum_key_value_headsÚslenr‚   s         r3   Ú	repeat_kvrµ   Æ   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 )NrN   r   rO   )rH   r;   )ÚpÚtrainingr   )rµ   Únum_key_value_groupsr/   Úmatmulr”   r   Ú
functionalÚsoftmaxÚfloat32r9   r;   r½   rÁ   Ú
contiguous)r·   r¸   r¹   rº   r»   r¼   r½   r¾   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r3   Úeager_attention_forwardrÌ   Ò   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   c                   óÎ   ‡ — 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z  dej        dz  d	e
dz  d
ee         de	ej        ej        f         fd„Zˆ xZS )ÚGemmaAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrc   Ú	layer_idxc                 óÎ  •— t          ¦   «                              ¦   «          || _        || _        t	          |d|j        |j        z  ¦  «        | _        |j        |j        z  | _	        | j        dz  | _
        |j        | _        t	          |d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 )Nr‚   g      à¿Úuse_bidirectional_attentionFra   )r+   r,   rc   rÏ   r„   rd   r…   r‚   r³   rÂ   r¼   Úattention_dropoutÚ	is_causalr   rf   Úattention_biasÚq_projÚk_projÚv_projÚo_proj©r1   rc   rÏ   r2   s      €r3   r,   zGemmaAttention.__init__ï   sR  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Ý$ VÐ-JÈEÑRÔRÐRˆ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r4   Nr®   Úposition_embeddingsr»   Úpast_key_valuesr¾   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        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )NrO   r   rN   r¶   )r½   r¼   )r[   r‚   rÕ   Úviewr”   rÖ   r×   r­   ÚupdaterÏ   r   Úget_interfacerc   Ú_attn_implementationrÌ   rÁ   rÒ   r¼   r±   rÇ   rØ   )r1   r®   rÚ   r»   rÛ   r¾   Úinput_shapeÚhidden_shapeÚquery_statesrÈ   rÉ   r–   r—   Úattention_interfacerË   rÊ   s                   r3   r8   zGemmaAttention.forward  sÀ  € ð $Ô)¨#¨2¨#Ô.ˆØ8˜Ð8 bÐ8¨$¬-Ð8Ð8ˆà—{’{ =Ñ1Ô1×6Ò6°|ÑDÔD×NÒNÈqÐRSÑTÔTˆØ—[’[ Ñ/Ô/×4Ò4°\ÑBÔB×LÒLÈQÐPQÑRÔRˆ
Ø—{’{ =Ñ1Ô1×6Ò6°|ÑDÔD×NÒNÈqÐRSÑTÔTˆ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(r4   r�   )r<   r=   r>   r?   r    r@   r,   r/   rB   rZ   r	   r   r   r8   rC   rD   s   @r3   rÎ   rÎ   ë   så   ø€ € € € € àGÐGð
˜{ð 
°sð 
ð 
ð 
ð 
ð 
ð 
ð4 IMØ.2Ø(,ð&)ð &)à”|ð&)ð # 5¤<°´Ð#=Ô>ÀÑEð&)ð œ tÑ+ð	&)ð
  ™ð&)ð Ð+Ô,ð&)ð 
ˆuŒ|˜Uœ\Ð)Ô	*ð&)ð &)ð &)ð &)ð &)ð &)ð &)ð &)r4   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GemmaDecoderLayerrc   rÏ   c                 ó4  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        |j        ¬¦  «        | _	        t          |j        |j        ¬¦  «        | _
        d S )N)rc   rÏ   ©rI   )r+   r,   rd   rÎ   Ú	self_attnr^   ÚmlprF   Úrms_norm_epsÚinput_layernormÚpost_attention_layernormrÙ   s      €r3   r,   zGemmaDecoderLayer.__init__0  sƒ   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔå'¨vÀÐKÑKÔKˆŒå˜FÑ#Ô#ˆŒÝ+¨FÔ,>ÀFÔDWÐXÑXÔXˆÔÝ(4°VÔ5GÈVÔM`Ð(aÑ(aÔ(aˆÔ%Ð%Ð%r4   NFr®   r»   r˜   rÛ   Ú	use_cacherÚ   r¾   r   c           
      óÎ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r®   r»   r˜   rÛ   rî   rÚ   © )rì   ré   rí   rê   )
r1   r®   r»   r˜   rÛ   rî   rÚ   r¾   ÚresidualÚ_s
             r3   r8   zGemmaDecoderLayer.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r4   )NNNFN)r<   r=   r>   r    r@   r,   r/   rB   Ú
LongTensorr	   ÚboolrZ   r   r   r8   rC   rD   s   @r3   ræ   ræ   /  sÿ   ø€ € € € € ðb˜{ð b°sð bð bð bð bð bð bð /3Ø04Ø(,Ø!&ØHLðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r4   ræ   c                   ó†   ‡ — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZ ej        ¦   «         ˆ fd„¦   «         Zˆ xZS )ÚGemmaPreTrainedModelrc   ÚmodelTræ   rÛ   )r®   Ú
attentionsc                 ó  •— t          ¦   «                              |¦  «         d|j        j        v rt	          j        |j        ¦  «         d S t          |t          ¦  «        r!t	          j	        |j
        |j        ¦  «         d S d S )NÚRMSNorm)r+   Ú_init_weightsr2   r<   ÚinitÚzeros_r:   r‘   r"   Ú	constant_r'   r-   )r1   r·   r2   s     €r3   rû   z"GemmaPreTrainedModel._init_weightsl  s‚   ø€ å‰Œ×Ò˜fÑ%Ô%Ð%à˜Ô(Ô1Ð1Ð1ÝŒK˜œÑ&Ô&Ð&Ð&Ð&Ý˜Õ <Ñ=Ô=ð 	JÝŒN˜6Ô-¨vÔ/HÑIÔIÐIÐIÐIð	Jð 	Jr4   )r<   r=   r>   r    rž   Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendræ   rÎ   Ú_can_record_outputsr/   r    rû   rC   rD   s   @r3   rö   rö   Z  s±   ø€ € € € € € àÐÐÑØÐØ&*Ð#Ø,Ð-ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà*Ø$ðð Ðð
 €U„]�_„_ðJð Jð Jð Jñ „_ðJð Jð Jð Jð Jr4   rö   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
GemmaModelrc   c                 óò  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          ‰j        ‰j        | j        | j        j        dz  ¬¦  «        | _        t          j
        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ‰j        ¬¦  «        | _        t#          ‰¬¦  «        | _        d| _        |                      ¦   «          d S )Ng      à?)r'   c                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS rð   )ræ   )Ú.0rÏ   rc   s     €r3   ú
<listcomp>z'GemmaModel.__init__.<locals>.<listcomp>�  s$   ø€ ÐcÐcÐc°iÕ˜v yÑ1Ô1ÐcÐcÐcr4   rè   ©rc   F)r+   r,   Úpad_token_idr&   Ú
vocab_sizer"   rd   rc   Úembed_tokensr   Ú
ModuleListÚrangeÚnum_hidden_layersÚlayersrF   rë   Únormro   Ú
rotary_embÚgradient_checkpointingÚ	post_initrl   s    `€r3   r,   zGemmaModel.__init__x  sì   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒå8ØÔ˜vÔ1°4Ô3CÐQUÔQ\ÔQhÐjmÑQmð
ñ 
ô 
ˆÔõ ”mØcÐcÐcÐcÅ5ÈÔIaÑCbÔCbÐcÑcÔcñ
ô 
ˆŒõ ! Ô!3¸Ô9LÐMÑMÔMˆŒ	Ý.°fÐ=Ñ=Ô=ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr4   Nr5   r»   r˜   rÛ   Úinputs_embedsrî   r¾   r   c           
      óP  — |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }t          | j        ||||¬¦  «        }	|}
|                      |
|¬¦  «        }| j        d | j        j        …         D ]} ||
f|	||||dœ|¤Ž}
Œ|                      |
¦  «        }
t          |
|r|nd ¬	¦  «        S )
Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )r|   )rc   r  r»   rÛ   r˜   )r˜   )r»   r˜   rÛ   rî   rÚ   )Úlast_hidden_staterÛ   )Ú
ValueErrorr  r
   rc   Úget_seq_lengthr/   r†   r[   r|   r§   r   r  r  r  r  r   )r1   r5   r»   r˜   rÛ   r  rî   r¾   Úpast_seen_tokensÚcausal_maskr®   rÚ   Údecoder_layers                r3   r8   zGemmaModel.forwardŠ  s“  € ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàÐ Ø ×-Ò-¨iÑ8Ô8ˆMàð 	?˜Ð0Ý*°$´+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)Ø /Ø#Ø$7ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝ&Ø+Ø/8ÐB˜O˜O¸dð
ñ 
ô 
ð 	
r4   )NNNNNN)r<   r=   r>   r    r,   r   r   r   r/   ró   rB   r	   ÚFloatTensorrô   r   r   r   r8   rC   rD   s   @r3   r
  r
  v  s  ø€ € € € € ð˜{ð ð ð ð ð ð ð$  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
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GemmaForCausalLMz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
  r÷   r  r   rf   rd   r&  r  rl   s     €r3   r,   zGemmaForCausalLM.__init__È  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   r5   r»   r˜   rÛ   r  Úlabelsrî   Úlogits_to_keepr¾   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 )a|  
        Example:

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

        >>> model = GemmaForCausalLM.from_pretrained("google/gemma-7b")
        >>> tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")

        >>> prompt = "What is your favorite condiment?"
        >>> 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]
        "What is your favorite condiment?"
        ```)r5   r»   r˜   rÛ   r  rî   N)r(  r*  r  )Úlossr(  rÛ   r®   rø   rð   )r÷   r  r‘   r@   Úslicer&  Úloss_functionrc   r  r   rÛ   r®   rø   )r1   r5   r»   r˜   rÛ   r  r*  rî   r+  r¾   Úoutputsr®   Úslice_indicesr(  r-  s                  r3   r8   zGemmaForCausalLM.forwardÑ  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   )r<   r=   r>   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr,   r   r   r/   ró   rB   r	   r#  rô   r@   r   r   r   r8   rC   rD   s   @r3   r%  r%  Â  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 ˜$‘;ð6
ð ˜eœlÑ*ð6
ð Ð+Ô,ð6
ð 
 ð6
ð 6
ð 6
ñ „^ñ Ôð6
ð 6
ð 6
ð 6
ð 6
r4   r%  c                   ó   — e Zd ZdS )ÚGemmaForSequenceClassificationN©r<   r=   r>   rð   r4   r3   r6  r6    ó   € € € € € Ø€Dr4   r6  c                   ó   — e Zd ZdS )ÚGemmaForTokenClassificationNr7  rð   r4   r3   r:  r:    r8  r4   r:  )r
  r%  r6  r:  rö   )r   )r¶   )DÚcollections.abcr   Útypingr   r/   r   Ú r   rü   Úactivationsr   Úcache_utilsr	   r
   Ú
generationr   Úintegrationsr   r   Úmasking_utilsr   Úmodeling_layersr   r   r   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_gemmar    Ú	Embeddingr"   ÚModulerF   r^   ro   r¤   r­   rB   r@   rµ   rA   rÌ   rÎ   ræ   rö   r
  r%  r6  r:  Ú__all__rð   r4   r3   ú<module>rO     sú  ðð. %Ð $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 IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ /Ð /Ð /Ð /Ð /Ð /ðð ð ð ð ð ð ð ð ð ð
 PÐ 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Sð Sð Sð Sð S 2¤<ñ Sô Sð Sð=ð =ð =ð =ð =�2”9ñ =ô =ð =ð(ð ð ð ð ˆrŒyñ ô ð ð ><ð ><ð ><ð ><ð ><˜2œ9ñ ><ô ><ð ><ðB(ð (ð (ð ÐÐ*Ñ+Ô+ðð ð ñ ,Ô+ðð2	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@)ð @)ð @)ð @)ð @)�R”Yñ @)ô @)ñ +Ô*ð@)ðF(ð (ð (ð (ð (Ð2ñ (ô (ð (ðV ðJð Jð Jð Jð J˜?ñ Jô Jñ „ðJð6 ðH
ð H
ð H
ð H
ð H
Ð%ñ H
ô H
ñ „ðH
ðV 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	ð 	ð 	ð 	ð 	Ð"?ÐAUñ 	ô 	ð 	ðð ð €€€r4   