Ë
    ÜÓ^j"U  ã                   óP  — 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	m
Z
 ddlmZ dd	lmZmZ dd
lmZmZ ddlmZ ddlmZ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$m%Z%m&Z&m'Z' ddl(m)Z)m*Z* ddl+m,Z, ddl-m.Z.  G d„ dej^                  «      Z0d„ Z1 ed«      d9d„«       Z2dejf                  de4dejf                  fd„Z5	 d:dej^                  d ejf                  d!ejf                  d"ejf                  d#ejf                  dz  d$e6d%e6d&e#e%   fd'„Z7 ee2«       G d(„ d)ej^                  «      «       Z8 G d*„ d+e«      Z9e& G d,„ d-e!«      «       Z: G d.„ d/ej^                  «      Z;e& G d0„ d1e:«      «       Z<e& G d2„ d3e:e«      «       Z= G d4„ d5ee:«      Z> G d6„ d7ee:«      Z?g d8¢Z@y);é    )ÚCallable)ÚOptionalN)Únné   )ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_func_from_hubÚuse_kernelized_func)Úcreate_causal_maskÚ!create_sliding_window_causal_mask)ÚFlashAttentionKwargs)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Starcoder2Configc                   óh   ‡ — e Zd Zdefˆ fd„Zdeej                     dz  dej                  fd„Zˆ xZ	S )ÚStarcoder2MLPÚconfigc                 óP  •— t         ‰| �  «        |j                  }t        j                  ||j
                  |j                  ¬«      | _        t        j                  |j
                  ||j                  ¬«      | _        t        |j                     | _        |j                  | _        y )N©Úbias)ÚsuperÚ__init__Úhidden_sizer   ÚLinearÚintermediate_sizeÚuse_biasÚc_fcÚc_projr   Ú
hidden_actÚactÚresidual_dropout)Úselfr$   Ú	embed_dimÚ	__class__s      €ú}/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/starcoder2/modeling_starcoder2.pyr)   zStarcoder2MLP.__init__6   su   ø€ Ü‰ÑÔØ×&Ñ&ˆ	Ü—I‘I˜i¨×)AÑ)AÈÏÉÔXˆŒ	Ü—i‘i × 8Ñ 8¸)È&Ï/É/ÔZˆŒÜ˜&×+Ñ+Ñ,ˆŒØ &× 7Ñ 7ˆÕó    Úhidden_statesNÚreturnc                 óØ   — | j                  |«      }| j                  |«      }| j                  |«      }t        j                  j                  || j                  | j                  ¬«      }|S )N©ÚpÚtraining)r.   r1   r/   r   Ú
functionalÚdropoutr2   r=   )r3   r8   s     r6   ÚforwardzStarcoder2MLP.forward>   sZ   € ØŸ	™	 -Ó0ˆØŸ™ Ó/ˆØŸ™ MÓ2ˆÜŸ™×-Ñ-¨m¸t×?TÑ?TÐ_c×_lÑ_lÐ-ÓmˆØÐr7   )
Ú__name__Ú
__module__Ú__qualname__r!   r)   ÚtupleÚtorchÚFloatTensorr@   Ú__classcell__©r5   s   @r6   r#   r#   5   s9   ø„ ð8Ð/õ 8ð U¨5×+<Ñ+<Ñ%=ÀÑ%Dð È×IZÑIZ÷ r7   r#   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..Néÿÿÿÿé   ©Údim)ÚshaperE   Úcat)ÚxÚx1Úx2s      r6   Úrotate_halfrS   F   sZ   € à	
ˆ3Ð"�!—'‘'˜"‘+ Ñ"Ð"Ð"Ñ	#€BØ	
ˆ3�—‘˜‘˜qÑ Ñ"Ð"Ñ	#€BÜ�9‰9�r�c˜2�Y BÔ'Ð'r7   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	unsqueezerS   )ÚqÚkÚcosÚsinÚunsqueeze_dimÚq_embedÚk_embeds          r6   Úapply_rotary_pos_embr^   M   sY   € ð& �-‰-˜Ó
&€CØ
�-‰-˜Ó
&€CØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�GÐÐr7   r8   Ún_repr9   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)rN   ÚexpandÚreshape)r8   r_   ÚbatchÚnum_key_value_headsÚslenÚhead_dims         r6   Ú	repeat_kvrg   g   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Tr7   ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingr?   Ú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 )NrK   r   rJ   )rM   Údtyper;   r    )rg   Únum_key_value_groupsrE   ÚmatmulÚ	transposer   r>   ÚsoftmaxÚfloat32Útorp   r?   r=   Ú
contiguous)rh   ri   rj   rk   rl   rm   r?   rn   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r6   Úeager_attention_forwardr|   s   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$Ð$r7   c                   ó  ‡ — e Zd ZdZddededz  fˆ fd„Z	 ddej                  de	ej                  ej                  f   dej                  dz  d	e
dz  d
ee   de	ej                  ej                  dz  e	ej                     dz  f   fd„Zˆ xZS )ÚStarcoder2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperNr$   Ú	layer_idxc                 óŽ  •— t         ‰| �  «        || _        || _        t	        |dd «      xs |j
                  |j                  z  | _        |j                  |j                  z  | _	        | j                  dz  | _
        |j                  | _        d| _        t        j                  |j
                  |j                  | j                  z  |j                  ¬«      | _        t        j                  |j
                  |j                  | j                  z  |j                  ¬«      | _        t        j                  |j
                  |j                  | j                  z  |j                  ¬«      | _        t        j                  |j                  | j                  z  |j
                  |j                  ¬«      | _        |j(                  | _        y )Nrf   g      à¿Tr&   )r(   r)   r$   r   Úgetattrr*   Únum_attention_headsrf   rd   rq   rm   Úattention_dropoutÚ	is_causalr   r+   r-   Úq_projÚk_projÚv_projÚo_projr2   ©r3   r$   r   r5   s      €r6   r)   zStarcoder2Attention.__init__�   sX  ø€ Ü‰ÑÔØˆŒØ"ˆŒÜ ¨
°DÓ9Òm¸V×=OÑ=OÐSY×SmÑSmÑ=mˆŒØ$*×$>Ñ$>À&×B\ÑB\Ñ$\ˆÔ!Ø—}‘} dÑ*ˆŒØ!'×!9Ñ!9ˆÔØˆŒÜ—i‘i × 2Ñ 2°F×4NÑ4NÐQU×Q^ÑQ^Ñ4^Ðek×etÑetÔuˆŒÜ—i‘i × 2Ñ 2°F×4NÑ4NÐQU×Q^ÑQ^Ñ4^Ðek×etÑetÔuˆŒÜ—i‘i × 2Ñ 2°F×4NÑ4NÐQU×Q^ÑQ^Ñ4^Ðek×etÑetÔuˆŒÜ—i‘i × :Ñ :¸T¿]¹]Ñ JÈF×L^ÑL^Ðek×etÑetÔuˆŒØ &× 7Ñ 7ˆÕr7   r8   Úposition_embeddingsrl   Úpast_key_valuesrn   r9   c           
      ó¢  — |j                   d d }g |¢d‘| j                  ‘­}| j                  |«      j                  |«      j	                  dd«      }| j                  |«      j                  |«      j	                  dd«      }	| j                  |«      j                  |«      j	                  dd«      }
|\  }}t        ||	||«      \  }}	|� |j                  |	|
| j                  «      \  }	}
t        j                  | j                  j                  t        «      } || ||	|
|f| j                  sdn| j                   | j"                  t%        | j                  dd «      dœ|¤Ž\  }} |j&                  g |¢d‘­Ž j)                  «       }| j+                  |«      }t,        j.                  j1                  || j2                  | j                  ¬«      }||fS )NrJ   r    rK   ç        Úsliding_window)r?   rm   rŽ   r;   )rN   rf   r…   Úviewrs   r†   r‡   r^   Úupdater   r   Úget_interfacer$   Ú_attn_implementationr|   r=   rƒ   rm   r�   rb   rw   rˆ   r   r>   r?   r2   )r3   r8   rŠ   rl   r‹   rn   Úinput_shapeÚhidden_shapeÚquery_statesrx   ry   rY   rZ   Úattention_interfacer{   rz   s                   r6   r@   zStarcoder2Attention.forwardŸ   sÎ  € 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‘LÜ" 4§;¡;Ð0@À$ÓGñ
%
ð ñ
%
Ñ!ˆ�\ð *�k×)Ñ)Ð;¨;Ð;¸Ò;×FÑFÓHˆØ—k‘k +Ó.ˆÜ—m‘m×+Ñ+Ø˜4×0Ñ0¸4¿=¹=ð ,ó 
ˆð ˜LÐ(Ð(r7   ©N)rA   rB   rC   Ú__doc__r!   Úintr)   rE   ÚTensorrD   r   r   r   r@   rG   rH   s   @r6   r~   r~   Œ   s²   ø„ áGñ8Ð/ð 8¸CÀ$¹Jõ 8ð( )-ñ+)à—|‘|ð+)ð # 5§<¡<°·±Ð#=Ñ>ð+)ð Ÿ™ tÑ+ð	+)ð
  ™ð+)ð Ð-Ñ.ð+)ð 
ˆu�|‰|˜UŸ\™\¨DÑ0°%¸¿¹Ñ2EÈÑ2LÐLÑ	M÷+)r7   r~   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Starcoder2DecoderLayerr$   r   c                 óH  •— t         ‰| �  «        |j                  | _        t        ||¬«      | _        t        |«      | _        t        j                  |j                  |j                  ¬«      | _
        t        j                  |j                  |j                  ¬«      | _        y )N)r$   r   ©Úeps)r(   r)   r*   r~   Ú	self_attnr#   Úmlpr   Ú	LayerNormÚnorm_epsilonÚinput_layernormÚpost_attention_layernormr‰   s      €r6   r)   zStarcoder2DecoderLayer.__init__Î   st   ø€ Ü‰ÑÔØ!×-Ñ-ˆÔÜ,°FÀiÔPˆŒÜ  Ó(ˆŒÜ!Ÿ|™|¨F×,>Ñ,>ÀF×DWÑDWÔXˆÔÜ(*¯©°V×5GÑ5GÈV×M`ÑM`Ô(aˆÕ%r7   Nr8   rl   Úposition_idsr‹   Ú	use_cacherŠ   rn   r9   c           
      óÀ   — |}| j                  |«      } | j                  d||||||dœ|¤Ž\  }}	||z   }|}| j                  |«      }| j                  |«      }||z   }|S )N)r8   rl   r¦   r‹   r§   rŠ   © )r¤   r    r¥   r¡   )
r3   r8   rl   r¦   r‹   r§   rŠ   rn   ÚresidualÚ_s
             r6   r@   zStarcoder2DecoderLayer.forwardÖ   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r7   )NNNFN)rA   rB   rC   r!   r™   r)   rE   rš   Ú
LongTensorr   ÚboolrD   r   r   r@   rG   rH   s   @r6   rœ   rœ   Í   s¿   ø„ ðbÐ/ð b¸Cõ bð /3Ø04Ø(,Ø!&ØHLñà—|‘|ðð Ÿ™ tÑ+ðð ×&Ñ&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5§<¡<°·±Ð#=Ñ>ÀÑEðð Ð+Ñ,ðð 
�‰÷r7   rœ   c                   óJ   — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZy)ÚStarcoder2PreTrainedModelr$   ÚmodelTrœ   r‹   )r8   Ú
attentionsN)rA   rB   rC   r!   Ú__annotations__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_backendrœ   r~   Ú_can_record_outputsr©   r7   r6   r¯   r¯   ö   sQ   … àÓØÐØ&*Ð#Ø1Ð2ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà/Ø)ñÑr7   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Starcoder2RotaryEmbeddingÚinv_freqNr$   c                 ó®  •— t         ‰| �  «        |j                  | _        |j                  | _        || _        | j
                  j                  d   | _        | j                  }| j                  dk7  rt        | j                     } || j
                  |«      \  }| _
        | j                  d|d¬«       | j                  d|j                  «       d¬«       y )NÚ	rope_typeÚdefaultr¿   F)Ú
persistentÚoriginal_inv_freq)r(   r)   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr$   Úrope_parametersrÁ   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r3   r$   ÚdeviceÚrope_init_fnr¿   r5   s        €r6   r)   z"Starcoder2RotaryEmbedding.__init__  s¶   ø€ Ü‰ÑÔØ"(×"@Ñ"@ˆÔØ$*×$BÑ$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�$Ô(à×Ñ˜Z¨¸eÐÔDØ×ÑÐ0°(·.±.Ó2BÈuÐÕUr7   rÍ   ztorch.deviceÚseq_lenr9   ztorch.Tensorc                 ó  — | j                   d   }t        | dd«      xs | j                  | j                  z  }d}d|t	        j
                  d|dt        j                  ¬«      j                  |t        j                  ¬«      |z  z  z  }||fS )	a¨  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetarf   Ng      ð?r   rK   ©rp   )rÍ   rp   )	rÈ   r�   r*   r‚   rE   ÚarangeÚint64rv   Úfloat)r$   rÍ   rÏ   ÚbaserM   Úattention_factorr¿   s          r6   rÉ   z9Starcoder2RotaryEmbedding.compute_default_rope_parameters  s�   € ð& ×%Ñ% lÑ3ˆÜ�f˜j¨$Ó/Òc°6×3EÑ3EÈ×IcÑIcÑ3cˆàÐð Ø”U—\‘\ ! S¨!´5·;±;Ô?×BÑBÈ&ÔX]×XcÑXcÐBÓdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r7   c                 óN  — | j                   d d d …d f   j                  «       j                  |j                  d   dd«      j	                  |j
                  «      }|d d …d d d …f   j                  «       }t        |j
                  j                  t        «      r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d¬«      5  |j                  «       |j                  «       z  j                  dd«      }t        j                  ||fd¬	«      }|j                  «       | j                  z  }|j                  «       | j                  z  }	d d d «       j	                  |j                   ¬
«      	j	                  |j                   ¬
«      fS # 1 sw Y   ŒAxY w)Nr   rJ   r    ÚmpsÚcpuF)Údevice_typeÚenabledrK   rL   rÒ   )r¿   rÕ   ra   rN   rv   rÍ   Ú
isinstanceÚtypeÚstrr   rs   rE   rO   rY   rÊ   rZ   rp   )
r3   rP   r¦   Úinv_freq_expandedÚposition_ids_expandedrÛ   ÚfreqsÚembrY   rZ   s
             r6   r@   z!Starcoder2RotaryEmbedding.forward:  sR  € ð !ŸM™M¨$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$r—   )NNN)rA   rB   rC   rE   rš   r²   r!   r)   Ústaticmethodr   r™   rD   rÕ   rÉ   Úno_gradr   r@   rG   rH   s   @r6   r¾   r¾   	  s™   ø… Ø�l‰lÓñVÐ/õ Vð  à*.Ø+/Ø"ñ*Ø  4Ñ'ð*à˜Ñ(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ñ	%ò	*ó ð*ð: €U‡]�]ƒ_Øñ<ó ó ô<r7   r¾   c                   óî   ‡ — e Zd Zdef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dz  d
ee   deez  fd„«       «       Zˆ xZS )ÚStarcoder2Modelr$   c           	      óB  •— t         ‰| �  |«       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                  «      | _        t        j                  t        |j                  «      D �cg c]  }t        ||«      ‘Œ c}«      | _        t        j                  |j                  |j                  ¬«      | _        t#        |¬«      | _        d| _        |j(                  | _        | j+                  «        y c c}w )Nrž   ©r$   F)r(   r)   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr*   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersrœ   Úlayersr¢   r£   Únormr¾   Ú
rotary_embÚgradient_checkpointingÚembedding_dropoutÚ	post_initr‰   s      €r6   r)   zStarcoder2Model.__init__L  sØ   ø€ Ü‰Ñ˜Ô Ø!×.Ñ.ˆÔØ ×+Ñ+ˆŒäŸL™L¨×):Ñ):¸F×<NÑ<NÐPT×P`ÑP`ÓaˆÔÜ—m‘mÜHMÈf×NfÑNfÓHgÖh¸9Ô# F¨IÕ6Òhó
ˆŒô —L‘L ×!3Ñ!3¸×9LÑ9LÔMˆŒ	Ü3¸6ÔBˆŒØ&+ˆÔ#Ø!'×!9Ñ!9ˆÔð 	�‰Õùò is   ÂDNÚ	input_idsrl   r¦   r‹   Úinputs_embedsr§   rn   r9   c           
      óø  — |d u |d uz  rt        d«      ‚|€| j                  |«      }|r|€t        | j                  ¬«      }|€V|�|j	                  «       nd}t        j                  |j                  d   |j                  ¬«      |z   }|j                  d«      }| j                  j                  €t        nt        }	 |	| j                  ||||¬«      }
|}t        j                  j                  || j                   | 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_embedsré   r   r    )rÍ   )r$   rù   rl   r‹   r¦   r;   )r¦   )rl   r¦   r‹   r§   rŠ   )Úlast_hidden_stater‹   )Ú
ValueErrorrî   r	   r$   Úget_seq_lengthrE   rÓ   rN   rÍ   rV   rŽ   r   r   r   r>   r?   rö   r=   rô   rò   rñ   ró   r   )r3   rø   rl   r¦   r‹   rù   r§   rn   Úpast_seen_tokensÚmask_functionÚcausal_maskr8   rŠ   Údecoder_layers                 r6   r@   zStarcoder2Model.forward]  sŸ  € 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4ˆLà.2¯k©k×.HÑ.HÐ.PÕ*ÔVwˆÙ#Ø—;‘;Ø'Ø)Ø+Ø%ô
ˆð &ˆÜŸ™×-Ñ-Ø˜T×3Ñ3¸d¿m¹mð .ó 
ˆð #Ÿo™o¨mÈ,˜oÓWÐà!Ÿ[™[Ð)H¨4¯;©;×+HÑ+HÐIò 		ˆMÙ)Øðà*Ø)Ø /Ø#Ø$7ñð ñ‰Mð		ð Ÿ	™	 -Ó0ˆä&Ø+Ù/8˜Oô
ð 	
à>Bô
ð 	
r7   )NNNNNN)rA   rB   rC   r!   r)   r   r   rE   r¬   rš   r   rF   r­   r   r   rD   r   r@   rG   rH   s   @r6   rç   rç   J  sÌ   ø„ ðÐ/õ ð"  Øð .2Ø.2Ø04Ø(,Ø26Ø!%ñ7
à×#Ñ# dÑ*ð7
ð Ÿ™ tÑ+ð7
ð ×&Ñ&¨Ñ-ð	7
ð
  ™ð7
ð ×(Ñ(¨4Ñ/ð7
ð ˜$‘;ð7
ð Ð+Ñ,ð7
ð 
Ð(Ñ	(ò7
ó ó  ô7
r7   rç   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Starcoder2ForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr8   Úlogitsc                 óè   •— t         ‰| �  |«       t        |«      | _        |j                  | _        t        j                  |j                  |j                  d¬«      | _        | j                  «        y )NFr&   )
r(   r)   rç   r°   rì   r   r+   r*   r  r÷   )r3   r$   r5   s     €r6   r)   zStarcoder2ForCausalLM.__init__Ÿ  sU   ø€ Ü‰Ñ˜Ô Ü$ VÓ,ˆŒ
Ø ×+Ñ+ˆŒÜ—y‘y ×!3Ñ!3°V×5FÑ5FÈUÔSˆŒð 	�‰Õr7   Nrø   rl   r¦   r‹   rù   Úlabelsr§   Úlogits_to_keeprn   r9   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 )aí  
        Example:

        ```python
        >>> from transformers import AutoTokenizer, Starcoder2ForCausalLM

        >>> model = Starcoder2ForCausalLM.from_pretrained("meta-starcoder2/Starcoder2-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-starcoder2/Starcoder2-2-7b-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."
        ```)rø   rl   r¦   r‹   rù   r§   N)r  r  rì   )Úlossr  r‹   r8   r±   r©   )r°   rû   rÝ   r™   Úslicer  Úloss_functionr$   rì   r   r‹   r8   r±   )r3   rø   rl   r¦   r‹   rù   r  r§   r	  rn   Úoutputsr8   Úslice_indicesr  r  s                  r6   r@   zStarcoder2ForCausalLM.forward¨  sÙ   € ð> ,6¨4¯:©:ð ,
ØØ)Ø%Ø+Ø'Øñ,
ð ñ,
ˆð  ×1Ñ1ˆä8BÀ>ÔSVÔ8Wœ˜~˜o¨tÔ4Ð]kˆØ—‘˜mªA¨}ºaÐ,?Ñ@ÓAˆàˆØÐØ%�4×%Ñ%Ðp¨V¸FÈtÏ{É{×OeÑOeÑpÐioÑpˆDä%ØØØ#×3Ñ3Ø!×/Ñ/Ø×)Ñ)ô
ð 	
r7   )NNNNNNNr   )rA   rB   rC   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr)   r   r   rE   r¬   rš   r   rF   r­   r™   r   r   r   r@   rG   rH   s   @r6   r  r  ™  s  ø„ à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hôð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ñ6
à×#Ñ# dÑ*ð6
ð Ÿ™ tÑ+ð6
ð ×&Ñ&¨Ñ-ð	6
ð
  ™ð6
ð ×(Ñ(¨4Ñ/ð6
ð × Ñ  4Ñ'ð6
ð ˜$‘;ð6
ð ˜eŸl™lÑ*ð6
ð Ð+Ñ,ð6
ð 
 ò6
ó ó ô6
r7   r  c                   ó   — e Zd Zy)Ú#Starcoder2ForSequenceClassificationN©rA   rB   rC   r©   r7   r6   r  r  ã  ó   „ Ør7   r  c                   ó   — e Zd Zy)Ú Starcoder2ForTokenClassificationNr  r©   r7   r6   r  r  ç  r  r7   r  )r  rç   r¯   r  r  )r    )r�   )AÚcollections.abcr   Útypingr   rE   r   Úactivationsr   Úcache_utilsr   r	   Ú
generationr
   Úintegrationsr   r   Úmasking_utilsr   r   Úmodeling_flash_attention_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_starcoder2r!   ÚModuler#   rS   r^   rš   r™   rg   rÕ   r|   r~   rœ   r¯   r¾   rç   r  r  r  Ú__all__r©   r7   r6   ú<module>r,     sà  ðõ4 %Ý ã Ý å !ß .Ý )ß Iß RÝ B÷ñ ÷
 Pß Kß FÝ &ß IÑ Iß GÝ 5Ý 6ô�B—I‘Iô ò"(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=)˜"Ÿ)™)ó =)ó +ð=)ô@&Ð7ô &ðR ô ó ó ðô$>< §	¡	ô ><ðB ôK
Ð/ó K
ó ðK
ð\ ôF
Ð5°ó F
ó ðF
ôR	Ð*JÐLeô 	ô	Ð'DÐF_ô 	ò�r7   