§
    ‚Štj"U  ã                   óT  — 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$m%Z%m&Z&m'Z' ddl(m)Z)m*Z* ddl+m,Z, ddl-m.Z.  G d„ dej/        ¦  «        Z0d„ Z1 ed¦  «        d:d„¦   «         Z2dej3        de4dej3        fd„Z5	 d;d ej/        d!ej3        d"ej3        d#ej3        d$ej3        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/„ d0ej/        ¦  «        Z;e& G d1„ d2e:¦  «        ¦   «         Z<e& G d3„ d4e:e¦  «        ¦   «         Z= G d5„ d6ee:¦  «        Z> G d7„ d8ee:¦  «        Z?g d9¢Z@dS )<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                   óZ   ‡ — 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                 ó4  •— t          ¦   «                              ¦   «          |j        }t          j        ||j        |j        ¬¦  «        | _        t          j        |j        ||j        ¬¦  «        | _        t          |j
                 | _        |j        | _        d S )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      €úp/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/starcoder2/modeling_starcoder2.pyr)   zStarcoder2MLP.__init__6   s{   ø€ Ý‰Œ×ÒÑÔÐØÔ&ˆ	Ý”I˜i¨Ô)AÈÌÐXÑXÔXˆŒ	Ý”i Ô 8¸)È&Ì/ÐZÑZÔZˆŒÝ˜&Ô+Ô,ˆŒØ &Ô 7ˆÔÐÐó    Úhidden_statesNÚreturnc                 óÜ   — |                       |¦  «        }|                      |¦  «        }|                      |¦  «        }t          j                             || j        | j        ¬¦  «        }|S )N©ÚpÚtraining)r.   r1   r/   r   Ú
functionalÚdropoutr2   r=   )r3   r8   s     r6   ÚforwardzStarcoder2MLP.forward>   s^   € ØŸ	š	 -Ñ0Ô0ˆØŸš Ñ/Ô/ˆØŸš MÑ2Ô2ˆÝœ×-Ò-¨m¸tÔ?TÐ_cÔ_lÐ-ÑmÔmˆØÐr7   )
Ú__name__Ú
__module__Ú__qualname__r!   r)   ÚtupleÚtorchÚFloatTensorr@   Ú__classcell__©r5   s   @r6   r#   r#   5   sw   ø€ € € € € ð8Ð/ð 8ð 8ð 8ð 8ð 8ð 8ð U¨5Ô+<Ô%=ÀÑ%Dð ÈÔIZð ð ð ð ð ð ð ð r7   r#   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..Néÿÿÿÿé   ©Údim)ÚshaperE   Úcat)ÚxÚx1Úx2s      r6   Úrotate_halfrS   F   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'r7   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	unsqueezerS   )ÚqÚkÚcosÚsinÚunsqueeze_dimÚq_embedÚk_embeds          r6   Úapply_rotary_pos_embr^   M   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r7   r8   Ún_repr9   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)rN   ÚexpandÚreshape)r8   r_   ÚbatchÚnum_key_value_headsÚslenÚhead_dims         r6   Ú	repeat_kvrg   g   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Tr7   ç        ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingr?   Ú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 )NrK   r   rJ   )rM   Údtyper;   r    )rg   Únum_key_value_groupsrE   ÚmatmulÚ	transposer   r>   ÚsoftmaxÚfloat32Útorq   r?   r=   Ú
contiguous)ri   rj   rk   rl   rm   rn   r?   ro   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r6   Úeager_attention_forwardr}   s   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$Ð$r7   c                   óð   ‡ — 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$   Ú	layer_idxc                 óÊ  •— t          ¦   «                              ¦   «          || _        || _        t	          |dd ¦  «        p|j        |j        z  | _        |j        |j        z  | _	        | j        dz  | _
        |j        | _        d| _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        | j        z  |j        |j        ¬¦  «        | _        |j        | _        d S )Nrf   g      à¿Tr&   )r(   r)   r$   r€   Úgetattrr*   Únum_attention_headsrf   rd   rr   rn   Úattention_dropoutÚ	is_causalr   r+   r-   Úq_projÚk_projÚv_projÚo_projr2   ©r3   r$   r€   r5   s      €r6   r)   zStarcoder2Attention.__init__�   s9  ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒÝ ¨
°DÑ9Ô9Ðm¸VÔ=OÐSYÔSmÑ=mˆŒØ$*Ô$>À&ÔB\Ñ$\ˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐekÔetÐuÑuÔuˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐekÔetÐuÑuÔuˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐekÔetÐuÑuÔuˆŒÝ”i Ô :¸T¼]Ñ JÈFÔL^ÐekÔetÐuÑuÔuˆŒØ &Ô 7ˆÔÐÐr7   r8   Úposition_embeddingsrm   Úpast_key_valuesro   r9   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        t%          | j        dd ¦  «        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }t,          j                             || j        | j        ¬¦  «        }||fS )NrJ   r    rK   rh   Úsliding_window)r?   rn   rŽ   r;   )rN   rf   r†   Úviewrt   r‡   rˆ   r^   Úupdater€   r   Úget_interfacer$   Ú_attn_implementationr}   r=   r„   rn   r‚   rb   rx   r‰   r   r>   r?   r2   )r3   r8   r‹   rm   rŒ   ro   Úinput_shapeÚhidden_shapeÚquery_statesry   rz   rY   rZ   Úattention_interfacer|   r{   s                   r6   r@   zStarcoder2Attention.forwardŸ   sü  € ð $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”LÝ" 4¤;Ð0@À$ÑGÔGð
%
ð 
%
ð ð
%
ð 
%
Ñ!ˆ�\ð *�kÔ)Ð;¨;Ð;¸Ð;Ð;Ð;×FÒFÑHÔHˆØ—k’k +Ñ.Ô.ˆÝ”m×+Ò+Ø˜4Ô0¸4¼=ð ,ñ 
ô 
ˆð ˜LÐ(Ð(r7   ©N)rA   rB   rC   Ú__doc__r!   Úintr)   rE   ÚTensorrD   r   r   r   r@   rG   rH   s   @r6   r   r   Œ   sõ   ø€ € € € € àGÐGð8ð 8Ð/ð 8¸CÀ$¹Jð 8ð 8ð 8ð 8ð 8ð 8ð( )-ð+)ð +)à”|ð+)ð # 5¤<°´Ð#=Ô>ð+)ð œ tÑ+ð	+)ð
  ™ð+)ð Ð-Ô.ð+)ð 
ˆuŒ|˜Uœ\¨DÑ0°%¸¼Ô2EÈÑ2LÐLÔ	Mð+)ð +)ð +)ð +)ð +)ð +)ð +)ð +)r7   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Starcoder2DecoderLayerr$   r€   c                 óH  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          j        |j        |j	        ¬¦  «        | _
        t          j        |j        |j	        ¬¦  «        | _        d S )N)r$   r€   ©Úeps)r(   r)   r*   r   Ú	self_attnr#   Úmlpr   Ú	LayerNormÚnorm_epsilonÚinput_layernormÚpost_attention_layernormrŠ   s      €r6   r)   zStarcoder2DecoderLayer.__init__Î   s‡   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔÝ,°FÀiÐPÑPÔPˆŒÝ  Ñ(Ô(ˆŒÝ!œ|¨FÔ,>ÀFÔDWÐXÑXÔXˆÔÝ(*¬°VÔ5GÈVÔM`Ð(aÑ(aÔ(aˆÔ%Ð%Ð%r7   NFr8   rm   Úposition_idsrŒ   Ú	use_cacher‹   ro   r9   c           
      óÎ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r8   rm   r¦   rŒ   r§   r‹   © )r¤   r    r¥   r¡   )
r3   r8   rm   r¦   rŒ   r§   r‹   ro   ÚresidualÚ_s
             r6   r@   zStarcoder2DecoderLayer.forwardÖ   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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¸Cð 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 ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r7   rœ   c                   óL   — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZdS )ÚStarcoder2PreTrainedModelr$   ÚmodelTrœ   rŒ   )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   sl   € € € € € € àÐÐÑØÐØ&*Ð#Ø1Ð2ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà/Ø)ðð ÐÐÐr7   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Starcoder2RotaryEmbeddingÚinv_freqNr$   c                 ó²  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        | j        j        d         | _        | j        }| j        dk    rt          | j                 } || j        |¦  «        \  }| _
        |                      d|d¬¦  «         |                      d|                     ¦   «         d¬¦  «         d S )NÚ	rope_typeÚdefaultr¿   F)Ú
persistentÚoriginal_inv_freq)r(   r)   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr$   Úrope_parametersrÁ   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r3   r$   ÚdeviceÚrope_init_fnr¿   r5   s        €r6   r)   z"Starcoder2RotaryEmbedding.__init__  sÊ   ø€ Ý‰Œ×ÒÑÔÐØ"(Ô"@ˆÔØ$*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Ur7   rÍ   ztorch.deviceÚseq_lenr9   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_thetarf   Ng      ð?r   rK   ©rq   )rÍ   rq   )	rÈ   r‚   r*   rƒ   rE   ÚarangeÚint64rw   Úfloat)r$   rÍ   rÏ   ÚbaserM   Úattention_factorr¿   s          r6   rÉ   z9Starcoder2RotaryEmbedding.compute_default_rope_parameters  sŒ   € ð& Ô% lÔ3ˆÝ�f˜j¨$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)r7   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   rJ   r    ÚmpsÚcpuF)Údevice_typeÚenabledrK   rL   rÒ   )r¿   rÕ   ra   rN   rw   rÍ   Ú
isinstanceÚtypeÚstrr   rt   rE   rO   rY   rÊ   rZ   rq   )
r3   rP   r¦   Úinv_freq_expandedÚposition_ids_expandedrÛ   ÚfreqsÚembrY   rZ   s
             r6   r@   z!Starcoder2RotaryEmbedding.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*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   	  sú   ø€ € € € € € ØŒlÐÐÑðVð VÐ/ð Vð Vð Vð Vð Vð Vð  à*.Ø+/Ø"ð*ð *Ø  4Ñ'ð*à˜Ô(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ô	%ð	*ð *ð *ñ „\ð*ð: €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r7   r¾   c                   óØ   ‡ — e Zd Zdefˆ fd„Zee	 	 	 	 	 	 ddej        dz  dej	        dz  dej        dz  de
dz  dej        dz  d	edz  d
ee         deez  fd„¦   «         ¦   «         Zˆ xZS )ÚStarcoder2Modelr$   c                 ó   •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          j        ‰j        ‰j        ¬¦  «        | _        t!          ‰¬¦  «        | _        d| _        ‰j        | _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS r©   )rœ   )Ú.0r€   r$   s     €r6   ú
<listcomp>z,Starcoder2Model.__init__.<locals>.<listcomp>S  s$   ø€ ÐhÐhÐh¸9Õ# F¨IÑ6Ô6ÐhÐhÐhr7   rž   ©r$   F)r(   r)   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr*   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr¢   r£   Únormr¾   Ú
rotary_embÚgradient_checkpointingÚembedding_dropoutÚ	post_init©r3   r$   r5   s    `€r6   r)   zStarcoder2Model.__init__L  sá   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hÐhÐhÐhÍÈfÔNfÑHgÔHgÐhÑhÔhñ
ô 
ˆŒõ ”L Ô!3¸Ô9LÐMÑMÔMˆŒ	Ý3¸6ÐBÑBÔBˆŒØ&+ˆÔ#Ø!'Ô!9ˆÔð 	�ŠÑÔÐÐÐr7   NÚ	input_idsrm   r¦   rŒ   Úinputs_embedsr§   ro   r9   c           
      óÔ  — |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }| j        j
        €t          nt          }	 |	| j        ||||¬¦  «        }
|}t          j                             || j        | 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_embedsrì   r   r    )rÍ   )r$   rý   rm   rŒ   r¦   r;   )r¦   )rm   r¦   rŒ   r§   r‹   )Úlast_hidden_staterŒ   )Ú
ValueErrorrñ   r	   r$   Úget_seq_lengthrE   rÓ   rN   rÍ   rV   rŽ   r   r   r   r>   r?   rù   r=   r÷   rõ   rô   rö   r   )r3   rü   rm   r¦   rŒ   rý   r§   ro   Úpast_seen_tokensÚmask_functionÚcausal_maskr8   r‹   Údecoder_layers                 r6   r@   zStarcoder2Model.forward]  sÕ  € 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4ˆLà.2¬kÔ.HÐ.PÕ*Ð*ÕVwˆØ#�mØ”;Ø'Ø)Ø+Ø%ð
ñ 
ô 
ˆð &ˆÝœ×-Ò-Ø˜TÔ3¸d¼mð .ñ 
ô 
ˆð #Ÿošo¨mÈ,˜oÑWÔWÐà!œ[Ð)H¨4¬;Ô+HÐ)HÔIð 		ð 		ˆMØ)˜MØðà*Ø)Ø /Ø#Ø$7ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆå&Ø+Ø/8ÐB˜O˜O¸dð
ñ 
ô 
ð 	
r7   )NNNNNN)rA   rB   rC   r!   r)   r   r   rE   r¬   rš   r   rF   r­   r   r   rD   r   r@   rG   rH   s   @r6   rç   rç   J  s
  ø€ € € € € ðÐ/ð ð ð ð ð ð ð"  Øð .2Ø.2Ø04Ø(,Ø26Ø!%ð7
ð 7
àÔ# dÑ*ð7
ð œ tÑ+ð7
ð Ô&¨Ñ-ð	7
ð
  ™ð7
ð Ô(¨4Ñ/ð7
ð ˜$‘;ð7
ð Ð+Ô,ð7
ð 
Ð(Ñ	(ð7
ð 7
ð 7
ñ „_ñ  Ôð7
ð 7
ð 7
ð 7
ð 7
r7   rç   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Starcoder2ForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr8   Úlogitsc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S )NFr&   )
r(   r)   rç   r°   rï   r   r+   r*   r  rú   rû   s     €r6   r)   zStarcoder2ForCausalLM.__init__Ÿ  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r7   Nr   rü   rm   r¦   rŒ   rý   Úlabelsr§   Úlogits_to_keepro   r9   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 )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."
        ```)rü   rm   r¦   rŒ   rý   r§   N)r
  r  rï   )Úlossr
  rŒ   r8   r±   r©   )r°   rÿ   rÝ   r™   Úslicer  Úloss_functionr$   rï   r   rŒ   r8   r±   )r3   rü   rm   r¦   rŒ   rý   r  r§   r  ro   Úoutputsr8   Úslice_indicesr
  r  s                  r6   r@   zStarcoder2ForCausalLM.forward¨  sô   € ð> ,6¨4¬:ð ,
ØØ)Ø%Ø+Ø'Øð,
ð ,
ð ð,
ð ,
ˆð  Ô1ˆå8BÀ>ÕSVÑ8WÔ8WÐk�˜~˜o¨tÑ4Ô4Ð4Ð]kˆØ—’˜m¨A¨A¨A¨}¸a¸a¸aÐ,?Ô@ÑAÔAˆàˆØÐØ%�4Ô%Ðp¨V¸FÈtÌ{ÔOeÐpÐpÐioÐpÐpˆDå%ØØØ#Ô3Ø!Ô/ØÔ)ð
ñ 
ô 
ð 	
r7   )NNNNNNNr   )rA   rB   rC   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr)   r   r   rE   r¬   rš   r   rF   r­   r™   r   r   r   r@   rG   rH   s   @r6   r  r  ™  sK  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hðð ð ð ð ð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ð6
ð 6
àÔ# dÑ*ð6
ð œ tÑ+ð6
ð Ô&¨Ñ-ð	6
ð
  ™ð6
ð Ô(¨4Ñ/ð6
ð Ô  4Ñ'ð6
ð ˜$‘;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
r7   r  c                   ó   — e Zd ZdS )Ú#Starcoder2ForSequenceClassificationN©rA   rB   rC   r©   r7   r6   r  r  ã  ó   € € € € € Ø€Dr7   r  c                   ó   — e Zd ZdS )Ú Starcoder2ForTokenClassificationNr  r©   r7   r6   r  r  ç  r  r7   r  )r  rç   r¯   r  r  )r    )rh   )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>r0     s�  ðð4 %Ð $Ð $Ð $Ð $Ð $Ø Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð à !Ð !Ð !Ð !Ð !Ð !Ø .Ð .Ð .Ð .Ð .Ð .Ð .Ð .Ø )Ð )Ð )Ð )Ð )Ð )Ø IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ RÐ RÐ RÐ RÐ RÐ RÐ RÐ RØ BÐ BÐ BÐ BÐ BÐ Bðð ð ð ð ð ð ð ð ð ð
 PÐ OÐ OÐ OÐ OÐ OÐ OÐ OØ KÐ KÐ KÐ KÐ KÐ KÐ KÐ KØ FÐ FÐ FÐ FÐ FÐ FÐ FÐ FØ &Ð &Ð &Ð &Ð &Ð &Ø IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ GÐ GÐ GÐ GÐ GÐ GÐ GÐ GØ 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø 6Ð 6Ð 6Ð 6Ð 6Ð 6ðð ð ð ð �B”Iñ ô ð ð"(ð (ð (ð ÐÐ*Ñ+Ô+ðð ð ñ ,Ô+ðð2	U˜Uœ\ð 	U°#ð 	U¸%¼,ð 	Uð 	Uð 	Uð 	Uð& ð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð ð%ð ð%ð Ð'Ô(ð%ð %ð %ð %ð2 ÐÐ)Ñ*Ô*ð=)ð =)ð =)ð =)ð =)˜"œ)ñ =)ô =)ñ +Ô*ð=)ð@&ð &ð &ð &ð &Ð7ñ &ô &ð &ðR ðð ð ð ð  ñ ô ñ „ðð$><ð ><ð ><ð ><ð >< ¤	ñ ><ô ><ð ><ðB ðK
ð K
ð K
ð K
ð K
Ð/ñ K
ô K
ñ „ðK
ð\ ðF
ð F
ð F
ð F
ð F
Ð5°ñ F
ô F
ñ „ðF
ðR	ð 	ð 	ð 	ð 	Ð*JÐLeñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð'DÐF_ñ 	ô 	ð 	ðð ð €€€r7   