Ë
    ÛÓ^jÀW  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 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$m%Z%m&Z&m'Z' ddl(m)Z)m*Z* ddl+m,Z, ddl-m.Z.  G d„ dej^                  «      Z0 G d„ dejb                  «      Z2 G d„ dejb                  «      Z3 G d„ dejb                  «      Z4d„ Z5 ed«      d=d „«       Z6d!ejn                  d"e8d#ejn                  fd$„Z9	 d>d%ejb                  d&ejn                  d'ejn                  d(ejn                  d)ejn                  dz  d*e:d+e:d,e#e%   fd-„Z; ee6«       G d.„ d/ejb                  «      «       Z< G d0„ d1e«      Z=e& G d2„ d3e!«      «       Z>e& G d4„ d5e>«      «       Z?e& G d6„ d7e>e«      «       Z@ G d8„ d9ee>«      ZA G d:„ d;ee>«      ZBg d<¢ZCy)?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            	       óZ   ‡ — 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.
    Únum_embeddingsÚembedding_dimÚpadding_idxÚembed_scalec                 ó„   •— t         ‰| �  |||«       || _        | j                  dt	        j
                  |«      d¬«       y )Nr&   F©Ú
persistent)ÚsuperÚ__init__Úscalar_embed_scaleÚregister_bufferÚtorchÚtensor)Úselfr#   r$   r%   r&   Ú	__class__s        €ús/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/gemma/modeling_gemma.pyr+   z%GemmaTextScaledWordEmbedding.__init__7   s;   ø€ Ü‰Ñ˜¨¸ÔDØ"-ˆÔØ×Ñ˜]¬E¯L©L¸Ó,EÐRWÐÕXó    Ú	input_idsc                 ó‚   •— t         ‰| �  |«      | j                  j                  | j                  j
                  «      z  S ©N)r*   Úforwardr&   ÚtoÚweightÚdtype)r0   r4   r1   s     €r2   r7   z$GemmaTextScaledWordEmbedding.forward<   s2   ø€ Ü‰w‰˜yÓ)¨D×,<Ñ,<×,?Ñ,?ÀÇÁ×@QÑ@QÓ,RÑRÐRr3   )ç      ð?)Ú__name__Ú
__module__Ú__qualname__Ú__doc__ÚintÚfloatr+   r.   ÚTensorr7   Ú__classcell__©r1   s   @r2   r"   r"   2   sG   ø„ ññY sð Y¸3ð YÈSð YÐ_dõ Yð
S §¡÷ Sñ Sr3   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GemmaRMSNormÚdimÚepsc                 óŠ   •— t         ‰| �  «        || _        t        j                  t        j                  |«      «      | _        y r6   )r*   r+   rH   r   Ú	Parameterr.   Úzerosr9   )r0   rG   rH   r1   s      €r2   r+   zGemmaRMSNorm.__init__A   s.   ø€ Ü‰ÑÔØˆŒÜ—l‘l¤5§;¡;¨sÓ#3Ó4ˆ�r3   c                 óŒ   — |t        j                  |j                  d«      j                  dd¬«      | j                  z   «      z  S )Né   éÿÿÿÿT)Úkeepdim)r.   ÚrsqrtÚpowÚmeanrH   )r0   Úxs     r2   Ú_normzGemmaRMSNorm._normF   s4   € Ø”5—;‘;˜qŸu™u Q›xŸ}™}¨R¸˜}Ó>ÀÇÁÑIÓJÑJÐJr3   c                 ó¢   — | j                  |j                  «       «      }|d| j                  j                  «       z   z  }|j                  |«      S )Nr;   )rT   rA   r9   Útype_as)r0   rS   Úoutputs      r2   r7   zGemmaRMSNorm.forwardI   sC   € Ø—‘˜AŸG™G›IÓ&ˆð ˜3 §¡×!2Ñ!2Ó!4Ñ4Ñ5ˆØ�~‰~˜aÓ Ð r3   c                 ó^   — t        | j                  j                  «      › d| j                  › �S )Nz, eps=)Útupler9   ÚshaperH   )r0   s    r2   Ú
extra_reprzGemmaRMSNorm.extra_reprP   s'   € Ü˜Ÿ™×)Ñ)Ó*Ð+¨6°$·(±(°Ð<Ð<r3   )g�íµ ÷Æ°>)
r<   r=   r>   r@   rA   r+   rT   r7   r[   rC   rD   s   @r2   rF   rF   @   s&   ø„ ñ5˜Cð 5 eõ 5ò
Kò!ö=r3   rF   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚGemmaMLPc                 óÊ  •— t         ‰| �  «        || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d¬«      | _        t        j                  | j                  | j                  d¬«      | _        t        j                  | j                  | j                  d¬«      | _	        t        |j                     | _        y ©NF©Úbias)r*   r+   ÚconfigÚhidden_sizeÚintermediate_sizer   ÚLinearÚ	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©r0   rb   r1   s     €r2   r+   zGemmaMLP.__init__U   s¦   ø€ Ü‰ÑÔØˆŒØ!×-Ñ-ˆÔØ!'×!9Ñ!9ˆÔÜŸ™ 4×#3Ñ#3°T×5KÑ5KÐRWÔXˆŒÜ—y‘y ×!1Ñ!1°4×3IÑ3IÐPUÔVˆŒÜŸ™ 4×#9Ñ#9¸4×;KÑ;KÐRWÔXˆŒÜ˜V×.Ñ.Ñ/ˆ�r3   c                 óˆ   — | j                  | j                  | j                  |«      «      | j                  |«      z  «      }|S r6   )rh   rj   rf   rg   )r0   rS   rh   s      r2   r7   zGemmaMLP.forward_   s6   € Ø—N‘N 4§;¡;¨t¯~©~¸aÓ/@Ó#AÀDÇLÁLÐQRÃOÑ#SÓTˆ	ØÐr3   )r<   r=   r>   r+   r7   rC   rD   s   @r2   r]   r]   T   s   ø„ ô0ör3   r]   c                   óÄ   ‡ — 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_freqNrb   c                 ó®  •— t         ‰| �  «        |j                  | _        |j                  | _        || _        | j
                  j                  d   | _        | j                  }| j                  dk7  rt        | j                     } || j
                  |«      \  }| _
        | j                  d|d¬«       | j                  d|j                  «       d¬«       y )NÚ	rope_typeÚdefaultro   Fr(   Úoriginal_inv_freq)r*   r+   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrb   Úrope_parametersrq   Úcompute_default_rope_parametersr   Úattention_scalingr-   Úclone)r0   rb   ÚdeviceÚrope_init_fnro   r1   s        €r2   r+   zGemmaRotaryEmbedding.__init__g   s¶   ø€ Ü‰ÑÔØ"(×"@Ñ"@ˆÔØ$*×$BÑ$BˆÔ!àˆŒàŸ™×4Ñ4°[ÑAˆŒØ!%×!EÑ!EˆØ�>‰>˜YÒ&Ü.¨t¯~©~Ñ>ˆLÙ+7¸¿¹ÀVÓ+LÑ(ˆ�$Ô(à×Ñ˜Z¨¸eÐÔDØ×ÑÐ0°(·.±.Ó2BÈuÐÕUr3   r{   ztorch.deviceÚseq_lenÚreturnztorch.Tensorc                 ó  — | j                   d   }t        | dd«      xs | j                  | j                  z  }d}d|t	        j
                  d|dt        j                  ¬«      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   rM   ©r:   )r{   r:   )	rw   Úgetattrrc   Únum_attention_headsr.   ÚarangeÚint64r8   rA   )rb   r{   r}   ÚbaserG   Úattention_factorro   s          r2   rx   z4GemmaRotaryEmbedding.compute_default_rope_parametersw   s�   € ð& ×%Ñ% lÑ3ˆÜ�f˜j¨$Ó/Òc°6×3EÑ3EÈ×IcÑIcÑ3cˆàÐð Ø”U—\‘\ ! S¨!´5·;±;Ô?×BÑBÈ&ÔX]×XcÑXcÐBÓdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r3   c                 óN  — | j                   d d d …d f   j                  «       j                  |j                  d   dd«      j	                  |j
                  «      }|d d …d d d …f   j                  «       }t        |j
                  j                  t        «      r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d¬«      5  |j                  «       |j                  «       z  j                  dd«      }t        j                  ||fd¬	«      }|j                  «       | j                  z  }|j                  «       | j                  z  }	d d d «       j	                  |j                   ¬
«      	j	                  |j                   ¬
«      fS # 1 sw Y   ŒAxY w)Nr   rN   r   ÚmpsÚcpuF)Údevice_typeÚenabledrM   ©rG   r‚   )ro   rA   ÚexpandrZ   r8   r{   Ú
isinstanceÚtypeÚstrr   Ú	transposer.   ÚcatÚcosry   Úsinr:   )
r0   rS   Úposition_idsÚinv_freq_expandedÚposition_ids_expandedrŒ   ÚfreqsÚembr•   r–   s
             r2   r7   zGemmaRotaryEmbedding.forward•   sR  € ð !ŸM™M¨$²°4¨-Ñ8×>Ñ>Ó@×GÑGÈ×HZÑHZÐ[\ÑH]Ð_aÐcdÓe×hÑhÐij×iqÑiqÓrÐØ ,ªQ°²a¨ZÑ 8× >Ñ >Ó @Ðä'1°!·(±(·-±-ÄÔ'EÈ!Ï(É(Ï-É-Ð[`ÒJ`�a—h‘h—m’mÐfkˆÜ¨¸UÔCñ 	5Ø&×,Ñ,Ó.Ð1F×1LÑ1LÓ1NÑN×YÑYÐZ[Ð]^Ó_ˆEÜ—)‘)˜U E˜N°Ô3ˆCØ—'‘'“)˜d×4Ñ4Ñ4ˆCØ—'‘'“)˜d×4Ñ4Ñ4ˆC÷		5ð �v‰v˜AŸG™GˆvÓ$ c§f¡f°1·7±7 fÓ&;Ð;Ð;÷	5ð 	5ús   ÃBFÆF$r6   ©NNN)r<   r=   r>   r.   rB   Ú__annotations__r    r+   Ústaticmethodr   r@   rY   rA   rx   Úno_gradr   r7   rC   rD   s   @r2   rn   rn   d   s˜   ø… Ø�l‰lÓñV˜{õ Vð  à%)Ø+/Ø"ñ*Ø˜dÑ"ð*à˜Ñ(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ñ	%ò	*ó ð*ð: €U‡]�]ƒ_Øñ<ó ó ô<r3   rn   c                 óš   — | 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..NrN   rM   rŽ   )rZ   r.   r”   )rS   Úx1Úx2s      r2   Úrotate_halfr£   ¥   sZ   € à	
ˆ3Ð"�!—'‘'˜"‘+ Ñ"Ð"Ð"Ñ	#€BØ	
ˆ3�—‘˜‘˜qÑ Ñ"Ð"Ñ	#€BÜ�9‰9�r�c˜2�Y BÔ'Ð'r3   Úrotary_pos_embc                 óž   — |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.
    )Ú	unsqueezer£   )ÚqÚkr•   r–   Úunsqueeze_dimÚq_embedÚk_embeds          r2   Úapply_rotary_pos_embr¬   ¬   sY   € ð& �-‰-˜Ó
&€CØ
�-‰-˜Ó
&€CØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�GÐÐr3   Úhidden_statesÚn_repr~   c                 óª   — | j                   \  }}}}|dk(  r| S | dd…dd…ddd…dd…f   j                  |||||«      } | j                  |||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)rZ   r�   Úreshape)r­   r®   ÚbatchÚnum_key_value_headsÚslenr�   s         r2   Ú	repeat_kvr´   Æ   so   € ð
 2?×1DÑ1DÑ.€EÐ  hØ�‚zØÐØ!¢!¢Q¨ªa²Ð"2Ñ3×:Ñ:¸5ÐBUÐW\Ð^bÐdlÓm€MØ× Ñ  Ð(;¸eÑ(CÀTÈ8ÓTÐTr3   ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingÚdropoutÚkwargsc                 ó  — t        || j                  «      }t        || j                  «      }	t        j                  ||j	                  dd«      «      |z  }
|�|
|z   }
t
        j                  j                  |
dt        j                  ¬«      j                  |j                  «      }
t
        j                  j                  |
|| j                  ¬«      }
t        j                  |
|	«      }|j	                  dd«      j                  «       }||
fS )NrM   r   rN   )rG   r:   )ÚpÚtrainingr   )r´   Únum_key_value_groupsr.   Úmatmulr“   r   Ú
functionalÚsoftmaxÚfloat32r8   r:   r»   r¿   Ú
contiguous)rµ   r¶   r·   r¸   r¹   rº   r»   r¼   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r2   Úeager_attention_forwardrÊ   Ò   sà   € ô ˜3 × ;Ñ ;Ó<€JÜ˜U F×$?Ñ$?Ó@€Lä—<‘<  z×';Ñ';¸A¸qÓ'AÓBÀWÑL€LØÐ!Ø# nÑ4ˆä—=‘=×(Ñ(¨¸2ÄUÇ]Á]Ð(ÓS×VÑVÐW\×WbÑWbÓc€LÜ—=‘=×(Ñ(¨¸È6Ï?É?Ð(Ó[€LÜ—,‘,˜|¨\Ó:€KØ×'Ñ'¨¨1Ó-×8Ñ8Ó:€Kà˜Ð$Ð$r3   c                   óø   ‡ — 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' paperrb   Ú	layer_idxc                 ó|  •— 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                  ¬«      | _        y )Nr�   g      à¿Úuse_bidirectional_attentionFr`   )r*   r+   rb   rÍ   rƒ   rc   r„   r�   r²   rÀ   rº   Úattention_dropoutÚ	is_causalr   re   Úattention_biasÚq_projÚk_projÚv_projÚo_proj©r0   rb   rÍ   r1   s      €r2   r+   zGemmaAttention.__init__ï   sZ  ø€ Ü‰ÑÔØˆŒØ"ˆŒÜ ¨
°F×4FÑ4FÈ&×JdÑJdÑ4dÓeˆŒØ$*×$>Ñ$>À&×B\ÑB\Ñ$\ˆÔ!Ø—}‘} dÑ*ˆŒØ!'×!9Ñ!9ˆÔÜ$ VÐ-JÈEÓRÐRˆŒä—i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×&Ñ&¨¯©Ñ6¸×8JÑ8JÐQW×QfÑQfô
ˆ�r3   Nr­   Úposition_embeddingsr¹   Úpast_key_valuesr¼   r~   c                 ó
  — |j                   d d }g |¢d‘| j                  ‘­}| j                  |«      j                  |«      j	                  dd«      }| j                  |«      j                  |«      j	                  dd«      }	| j                  |«      j                  |«      j	                  dd«      }
|\  }}t        ||	||«      \  }}	|� |j                  |	|
| j                  «      \  }	}
t        j                  | j                  j                  t        «      } || ||	|
|f| j                  sdn| j                   | j"                  dœ|¤Ž\  }} |j$                  g |¢d‘­Ž j'                  «       }| j)                  |«      }||fS )NrN   r   rM   ç        )r»   rº   )rZ   r�   rÓ   Úviewr“   rÔ   rÕ   r¬   ÚupdaterÍ   r   Úget_interfacerb   Ú_attn_implementationrÊ   r¿   rÐ   rº   r°   rÅ   rÖ   )r0   r­   rØ   r¹   rÙ   r¼   Úinput_shapeÚhidden_shapeÚquery_statesrÆ   rÇ   r•   r–   Úattention_interfacerÉ   rÈ   s                   r2   r7   zGemmaAttention.forward  s‘  € ð $×)Ñ)¨#¨2Ð.ˆØ8˜Ð8 bÐ8¨$¯-©-Ñ8ˆà—{‘{ =Ó1×6Ñ6°|ÓD×NÑNÈqÐRSÓTˆØ—[‘[ Ó/×4Ñ4°\ÓB×LÑLÈQÐPQÓRˆ
Ø—{‘{ =Ó1×6Ñ6°|ÓD×NÑNÈqÐRSÓTˆà&‰ˆˆSÜ#7¸ÀjÐRUÐWZÓ#[Ñ ˆ�jàÐ&Ø'6×'=Ñ'=¸jÈ,ÐX\×XfÑXfÓ'gÑ$ˆJ˜ä(?×(MÑ(MØ�K‰K×,Ñ,Ô.Eó)
Ðñ %8ØØØØØð	%
ð  $Ÿ}š}‘C°$×2HÑ2HØ—L‘Lñ	%
ð ñ	%
Ñ!ˆ�\ð *�k×)Ñ)Ð;¨;Ð;¸Ò;×FÑFÓHˆØ—k‘k +Ó.ˆØ˜LÐ(Ð(r3   rœ   )r<   r=   r>   r?   r    r@   r+   r.   rB   rY   r	   r   r   r7   rC   rD   s   @r2   rÌ   rÌ   ë   s¥   ø„ áGð
˜{ð 
°sõ 
ð4 IMØ.2Ø(,ñ&)à—|‘|ð&)ð # 5§<¡<°·±Ð#=Ñ>ÀÑEð&)ð Ÿ™ tÑ+ð	&)ð
  ™ð&)ð Ð+Ñ,ð&)ð 
ˆu�|‰|˜UŸ\™\Ð)Ñ	*÷&)r3   rÌ   c                   ó  ‡ — 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GemmaDecoderLayerrb   rÍ   c                 ó   •— t         ‰| �  «        |j                  | _        t        ||¬«      | _        t        |«      | _        t        |j                  |j                  ¬«      | _	        t        |j                  |j                  ¬«      | _
        y )N)rb   rÍ   ©rH   )r*   r+   rc   rÌ   Ú	self_attnr]   ÚmlprF   Úrms_norm_epsÚinput_layernormÚpost_attention_layernormr×   s      €r2   r+   zGemmaDecoderLayer.__init__0  sl   ø€ Ü‰ÑÔØ!×-Ñ-ˆÔä'¨vÀÔKˆŒä˜FÓ#ˆŒÜ+¨F×,>Ñ,>ÀF×DWÑDWÔXˆÔÜ(4°V×5GÑ5GÈV×M`ÑM`Ô(aˆÕ%r3   Nr­   r¹   r—   rÙ   Ú	use_cacherØ   r¼   r~   c           
      óÀ   — |}| j                  |«      } | j                  d||||||dœ|¤Ž\  }}	||z   }|}| j                  |«      }| j                  |«      }||z   }|S )N)r­   r¹   r—   rÙ   rí   rØ   © )rë   rè   rì   ré   )
r0   r­   r¹   r—   rÙ   rí   rØ   r¼   ÚresidualÚ_s
             r2   r7   zGemmaDecoderLayer.forward:  s�   € ð !ˆØ×,Ñ,¨]Ó;ˆà)˜4Ÿ>™>ð 
Ø'Ø)Ø%Ø+ØØ 3ñ
ð ñ
Ñˆ�qð ! =Ñ0ˆð !ˆØ×5Ñ5°mÓDˆØŸ™ Ó/ˆØ  =Ñ0ˆØÐr3   )NNNFN)r<   r=   r>   r    r@   r+   r.   rB   Ú
LongTensorr	   ÚboolrY   r   r   r7   rC   rD   s   @r2   rå   rå   /  s¾   ø„ ðb˜{ð b°sõ bð /3Ø04Ø(,Ø!&ØHLñà—|‘|ðð Ÿ™ tÑ+ðð ×&Ñ&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5§<¡<°·±Ð#=Ñ>ÀÑEðð Ð+Ñ,ðð 
�‰÷r3   rå   c                   ó„   ‡ — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZ ej$                  «       ˆ fd„«       Zˆ xZS )ÚGemmaPreTrainedModelrb   ÚmodelTrå   rÙ   )r­   Ú
attentionsc                 ó
  •— t         ‰| �  |«       d|j                  j                  v r t	        j
                  |j                  «       y t        |t        «      r+t	        j                  |j                  |j                  «       y y )NÚRMSNorm)r*   Ú_init_weightsr1   r<   ÚinitÚzeros_r9   r�   r"   Ú	constant_r&   r,   )r0   rµ   r1   s     €r2   rú   z"GemmaPreTrainedModel._init_weightsl  s^   ø€ ä‰Ñ˜fÔ%à˜×(Ñ(×1Ñ1Ñ1Ü�K‰K˜Ÿ™Õ&Ü˜Ô <Ô=Ü�N‰N˜6×-Ñ-¨v×/HÑ/HÕIð >r3   )r<   r=   r>   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_backendrå   rÌ   Ú_can_record_outputsr.   rŸ   rú   rC   rD   s   @r2   rõ   rõ   Z  sp   ø… àÓØÐØ&*Ð#Ø,Ð-ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà*Ø$ñÐð
 €U‡]�]ƒ_óJó ôJr3   rõ   c                   óò   ‡ — 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
GemmaModelrb   c           	      ó*  •— t         ‰| �  |«       |j                  | _        |j                  | _        t        |j                  |j                  | j                  | j                  j                  dz  ¬«      | _        t        j                  t        |j                  «      D �cg c]  }t        ||«      ‘Œ c}«      | _        t        |j                  |j                   ¬«      | _        t%        |¬«      | _        d| _        | j+                  «        y c c}w )Ng      à?)r&   rç   ©rb   F)r*   r+   Úpad_token_idr%   Ú
vocab_sizer"   rc   rb   Úembed_tokensr   Ú
ModuleListÚrangeÚnum_hidden_layersrå   ÚlayersrF   rê   Únormrn   Ú
rotary_embÚgradient_checkpointingÚ	post_initr×   s      €r2   r+   zGemmaModel.__init__x  sÛ   ø€ Ü‰Ñ˜Ô Ø!×.Ñ.ˆÔØ ×+Ñ+ˆŒä8Ø×Ñ˜v×1Ñ1°4×3CÑ3CÐQU×Q\ÑQ\×QhÑQhÐjmÑQmô
ˆÔô —m‘mÜCHÈ×IaÑIaÓCbÖc°iÔ˜v yÕ1Òcó
ˆŒô ! ×!3Ñ!3¸×9LÑ9LÔMˆŒ	Ü.°fÔ=ˆŒØ&+ˆÔ#ð 	�‰Õùò ds   Â"DNr4   r¹   r—   rÙ   Úinputs_embedsrí   r¼   r~   c           
      óN  — |d u |d uz  rt        d«      ‚|€| j                  |«      }|r|€t        | j                  ¬«      }|€V|�|j	                  «       nd}t        j                  |j                  d   |j                  ¬«      |z   }|j                  d«      }t        | j                  ||||¬«      }	|}
| j                  |
|¬«      }| j                  d | j                  j                   D ]  } ||
f|	||||dœ|¤Ž}
Œ | j                  |
«      }
t        |
|r|¬	«      S d ¬	«      S )
Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )r{   )rb   r  r¹   rÙ   r—   )r—   )r¹   r—   rÙ   rí   rØ   )Úlast_hidden_staterÙ   )Ú
ValueErrorr  r
   rb   Úget_seq_lengthr.   r…   rZ   r{   r¦   r   r  r  r  r  r   )r0   r4   r¹   r—   rÙ   r  rí   r¼   Úpast_seen_tokensÚcausal_maskr­   rØ   Údecoder_layers                r2   r7   zGemmaModel.forwardŠ  s[  € ð ˜Ð -°tÐ";Ò<ÜÐYÓZÐZàÐ Ø ×-Ñ-¨iÓ8ˆMá˜Ð0Ü*°$·+±+Ô>ˆOàÐØCRÐC^˜×=Ñ=Ô?ÐdeÐÜ Ÿ<™<¨×(;Ñ(;¸AÑ(>À}×G[ÑG[Ô\Ð_oÑoˆLØ'×1Ñ1°!Ó4ˆLä(Ø—;‘;Ø'Ø)Ø+Ø%ô
ˆð &ˆØ"Ÿo™o¨mÈ,˜oÓWÐà!Ÿ[™[Ð)H¨4¯;©;×+HÑ+HÐIò 		ˆMÙ)Øðà*Ø)Ø /Ø#Ø$7ñð ñ‰Mð		ð Ÿ	™	 -Ó0ˆÜ&Ø+Ù/8˜Oô
ð 	
à>Bô
ð 	
r3   )NNNNNN)r<   r=   r>   r    r+   r   r   r   r.   rò   rB   r	   ÚFloatTensorró   r   r   r   r7   rC   rD   s   @r2   r	  r	  v  sÍ   ø„ ð˜{õ ð$  ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ñ2
à×#Ñ# dÑ*ð2
ð Ÿ™ tÑ+ð2
ð ×&Ñ&¨Ñ-ð	2
ð
  ™ð2
ð ×(Ñ(¨4Ñ/ð2
ð ˜$‘;ð2
ð Ð+Ñ,ð2
ð 
!ò2
ó ó ó  ô2
r3   r	  c                   óB  ‡ — 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                 óè   •— t         ‰| �  |«       t        |«      | _        |j                  | _        t        j                  |j                  |j                  d¬«      | _        | j                  «        y r_   )
r*   r+   r	  rö   r  r   re   rc   r"  r  rk   s     €r2   r+   zGemmaForCausalLM.__init__È  sU   ø€ Ü‰Ñ˜Ô Ü Ó'ˆŒ
Ø ×+Ñ+ˆŒÜ—y‘y ×!3Ñ!3°V×5FÑ5FÈUÔSˆŒð 	�‰Õr3   Nr4   r¹   r—   rÙ   r  Úlabelsrí   Úlogits_to_keepr¼   r~   c	           
      óx  —  | j                   d||||||dœ|	¤Ž}
|
j                  }t        |t        «      rt	        | d«      n|}| j                  |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?"
        ```)r4   r¹   r—   rÙ   r  rí   N)r$  r&  r  )Úlossr$  rÙ   r­   r÷   rï   )rö   r  r�   r@   Úslicer"  Úloss_functionrb   r  r   rÙ   r­   r÷   )r0   r4   r¹   r—   rÙ   r  r&  rí   r'  r¼   Úoutputsr­   Úslice_indicesr$  r)  s                  r2   r7   zGemmaForCausalLM.forwardÑ  sÙ   € ð> ,6¨4¯:©:ð ,
ØØ)Ø%Ø+Ø'Øñ,
ð ñ,
ˆð  ×1Ñ1ˆä8BÀ>ÔSVÔ8Wœ˜~˜o¨tÔ4Ð]kˆØ—‘˜mªA¨}ºaÐ,?Ñ@ÓAˆàˆØÐØ%�4×%Ñ%Ðp¨V¸FÈtÏ{É{×OeÑOeÑpÐioÑpˆDä%ØØØ#×3Ñ3Ø!×/Ñ/Ø×)Ñ)ô
ð 	
r3   )NNNNNNNr   )r<   r=   r>   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr+   r   r   r.   rò   rB   r	   r  ró   r@   r   r   r   r7   rC   rD   s   @r2   r!  r!  Â  s  ø„ à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hôð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ñ6
à×#Ñ# dÑ*ð6
ð Ÿ™ tÑ+ð6
ð ×&Ñ&¨Ñ-ð	6
ð
  ™ð6
ð ×(Ñ(¨4Ñ/ð6
ð × Ñ  4Ñ'ð6
ð ˜$‘;ð6
ð ˜eŸl™lÑ*ð6
ð Ð+Ñ,ð6
ð 
 ò6
ó ó ô6
r3   r!  c                   ó   — e Zd Zy)ÚGemmaForSequenceClassificationN©r<   r=   r>   rï   r3   r2   r2  r2    ó   „ Ør3   r2  c                   ó   — e Zd Zy)ÚGemmaForTokenClassificationNr3  rï   r3   r2   r6  r6    r4  r3   r6  )r	  r!  r2  r6  rõ   )r   )rÛ   )DÚcollections.abcr   Útypingr   r.   r   Ú r   rû   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]   rn   r£   r¬   rB   r@   r´   rA   rÊ   rÌ   rå   rõ   r	  r!  r2  r6  Ú__all__rï   r3   r2   ú<module>rK     s  ðõ. %Ý ã Ý å &Ý !ß .Ý )ß IÝ /÷ñ ÷
 Pß Kß FÝ &ß IÑ Iß GÝ 5Ý ,ôS 2§<¡<ô Sô=�2—9‘9ô =ô(ˆr�y‰yô ô ><˜2Ÿ9™9ô ><òB(ñ Ð*Ó+òó ,ðð2	U˜UŸ\™\ð 	U°#ð 	U¸%¿,¹,ó 	Uð& ñ%Ø�I‰Ið%à�<‰<ð%ð 
�‰ð%ð �<‰<ð	%ð
 —L‘L 4Ñ'ð%ð ð%ð ð%ð Ð'Ñ(ó%ñ2 Ð)Ó*ô@)�R—Y‘Yó @)ó +ð@)ôF(Ð2ô (ðV ôJ˜?ó Jó ðJð6 ôH
Ð%ó H
ó ðH
ðV ôF
Ð+¨_ó F
ó ðF
ôR	Ð%EÐG[ô 	ô	Ð"?ÐAUô 	ò�r3   