§
    ‚Štj²X  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 dd	l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.        ¦  «        Z/ G d„ de¦  «        Z0dej1        de2dej1        fd„Z3	 d;dej.        dej1        d ej1        d!ej1        d"ej1        dz  d#e4d$e4d%e"e$         fd&„Z5d'„ Z6d<d(„Z7 G d)„ d*ej.        ¦  «        Z8 G d+„ d,ej.        ¦  «        Z9 ed-¦  «         G d.„ d/ej.        ¦  «        ¦   «         Z:e% G d0„ d1e ¦  «        ¦   «         Z;e% G d2„ d3e;¦  «        ¦   «         Z<e% G d4„ d5e;e¦  «        ¦   «         Z= G d6„ d7ee;¦  «        Z> G d8„ d9ee;¦  «        Z?g d:¢Z@dS )=é    )ÚCallable)ÚOptionalNé   )ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_forward_from_hub)Úcreate_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
Glm4Configc                   óB   ‡ — e Zd Zˆ fd„Zdej        dej        fd„Zˆ xZS )ÚGlm4MLPc                 ó"  •— t          ¦   «                              ¦   «          || _        t          j        |j        d|j        z  d¬¦  «        | _        t          j        |j        |j        d¬¦  «        | _        t          |j
                 | _        d S )Né   F©Úbias)ÚsuperÚ__init__ÚconfigÚnnÚLinearÚhidden_sizeÚintermediate_sizeÚgate_up_projÚ	down_projr   Ú
hidden_actÚactivation_fn©Úselfr'   Ú	__class__s     €úd/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/glm4/modeling_glm4.pyr&   zGlm4MLP.__init__2   sz   ø€ Ý‰Œ×ÒÑÔÐàˆŒÝœI fÔ&8¸!¸fÔ>VÑ:VÐ]bÐcÑcÔcˆÔÝœ 6Ô#;¸VÔ=OÐV[Ð\Ñ\Ô\ˆŒÝ# FÔ$5Ô6ˆÔÐÐó    Úhidden_statesÚreturnc                 óº   — |                       |¦  «        }|                     dd¬¦  «        \  }}||                      |¦  «        z  }|                      |¦  «        S )Nr"   éÿÿÿÿ©Údim)r,   Úchunkr/   r-   )r1   r5   Ú	up_statesÚgates       r3   ÚforwardzGlm4MLP.forward:   sX   € Ø×%Ò% mÑ4Ô4ˆ	à#Ÿ/š/¨!°˜/Ñ4Ô4‰ˆˆiØ × 2Ò 2°4Ñ 8Ô 8Ñ8ˆ	à�~Š~˜iÑ(Ô(Ð(r4   )Ú__name__Ú
__module__Ú__qualname__r&   ÚtorchÚFloatTensorr>   Ú__classcell__©r2   s   @r3   r    r    1   s`   ø€ € € € € ð7ð 7ð 7ð 7ð 7ð) UÔ%6ð )¸5Ô;Lð )ð )ð )ð )ð )ð )ð )ð )r4   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ej        eej        ej        f         dz  f         fd„Zˆ xZS )ÚGlm4DecoderLayerr'   Ú	layer_idxc                 ó´  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        |j        ¬¦  «        | _	        t          |j        |j        ¬¦  «        | _
        t          |j        |j        ¬¦  «        | _        t          |j        |j        ¬¦  «        | _        d S )N)r'   rH   ©Úeps)r%   r&   r*   ÚGlm4AttentionÚ	self_attnr    ÚmlpÚGlm4RMSNormÚrms_norm_epsÚinput_layernormÚpost_attention_layernormÚpost_self_attn_layernormÚpost_mlp_layernorm©r1   r'   rH   r2   s      €r3   r&   zGlm4DecoderLayer.__init__D   s·   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔÝ&¨fÀ	ÐJÑJÔJˆŒå˜6‘?”?ˆŒÝ*¨6Ô+=À6ÔCVÐWÑWÔWˆÔÝ(3°FÔ4FÈFÔL_Ð(`Ñ(`Ô(`ˆÔ%Ý(3°FÔ4FÈFÔL_Ð(`Ñ(`Ô(`ˆÔ%Ý"-¨fÔ.@ÀfÔFYÐ"ZÑ"ZÔ"ZˆÔÐÐr4   NFr5   Úattention_maskÚposition_idsÚpast_key_valuesÚ	use_cacheÚposition_embeddingsÚkwargsr6   c           
      ó"  — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	|                      |¦  «        }||z   }|}|                      |¦  «        }|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r5   rV   rW   rX   rY   rZ   © )rQ   rM   rS   rR   rN   rT   )
r1   r5   rV   rW   rX   rY   rZ   r[   ÚresidualÚ_s
             r3   r>   zGlm4DecoderLayer.forwardO   sÅ   € ð !ˆØ×,Ò,¨]Ñ;Ô;ˆà)˜4œ>ð 
Ø'Ø)Ø%Ø+ØØ 3ð
ð 
ð ð
ð 
Ñˆ�qð ×5Ò5°mÑDÔDˆØ  =Ñ0ˆà ˆØ×5Ò5°mÑDÔDˆØŸš Ñ/Ô/ˆØ×/Ò/°Ñ>Ô>ˆØ  =Ñ0ˆØÐr4   )NNNFN)r?   r@   rA   r   Úintr&   rB   ÚTensorÚ
LongTensorr   ÚboolÚtupler   r   rC   r>   rD   rE   s   @r3   rG   rG   C   s   ø€ € € € € ð	[˜zð 	[°cð 	[ð 	[ð 	[ð 	[ð 	[ð 	[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 
ˆuÔ  %¨Ô(9¸5Ô;LÐ(LÔ"MÐPTÑ"TÐTÔ	Uðð ð ð ð ð ð ð r4   rG   r5   Ún_repr6   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)ÚshapeÚexpandÚreshape)r5   re   ÚbatchÚnum_key_value_headsÚslenÚhead_dims         r3   Ú	repeat_kvrn   q   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valuerV   ÚscalingÚdropoutr[   c                 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 )Nr"   r   r8   )r:   Údtype)ÚpÚtrainingr   )rn   Únum_key_value_groupsrB   ÚmatmulÚ	transposer(   Ú
functionalÚsoftmaxÚfloat32Útorw   ru   ry   Ú
contiguous)rp   rq   rr   rs   rV   rt   ru   r[   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r3   Úeager_attention_forwardr†   }   sé   € õ ˜3 Ô ;Ñ<Ô<€JÝ˜U FÔ$?Ñ@Ô@€Lå”<  z×';Ò';¸A¸qÑ'AÔ'AÑBÔBÀWÑL€LØÐ!Ø# nÑ4ˆå”=×(Ò(¨¸2ÅUÄ]Ð(ÑSÔS×VÒVÐW\ÔWbÑcÔc€LÝ”=×(Ò(¨¸È6Ì?Ð(Ñ[Ô[€LÝ”,˜|¨\Ñ:Ô:€KØ×'Ò'¨¨1Ñ-Ô-×8Ò8Ñ:Ô:€Kà˜Ð$Ð$r4   c                 óŽ   — | dddd…f         }| dddd…f         }t          j        | |fd¬¦  «                             d¦  «        S )	z*Rotates half the hidden dims of the input..r   Nr"   r   r8   r9   éþÿÿÿ)rB   ÚstackÚflatten)ÚxÚx1Úx2s      r3   Úrotate_halfrŽ   –   sQ   € à	
ˆ3���1�ˆ9Œ€BØ	
ˆ3���1�ˆ9Œ€BÝŒ;˜˜˜R�y bÐ)Ñ)Ô)×1Ò1°"Ñ5Ô5Ð5r4   c                 óT  — |                      |¦  «        }|                      |¦  «        }|dd|j        d         dz  …f                              dd¬¦  «        }|dd|j        d         dz  …f                              dd¬¦  «        }|j        d         }| dd|…f         | d|d…f         }}|dd|…f         |d|d…f         }	}||z  t          |¦  «        |z  z   }
||z  t          |¦  «        |z  z   }t	          j        |
|gd¬¦  «        }
t	          j        ||	gd¬¦  «        }|
|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.
    .Nr8   r"   r9   )Ú	unsqueezerg   Úrepeat_interleaverŽ   rB   Úcat)ÚqÚkÚcosÚsinÚunsqueeze_dimÚ
rotary_dimÚq_rotÚq_passÚk_rotÚk_passÚq_embedÚk_embeds               r3   Úapply_rotary_pos_embrŸ   �   s\  € ð$ �-Š-˜Ñ
&Ô
&€CØ
�-Š-˜Ñ
&Ô
&€Cð ˆcÐ'�S”Y˜r”] aÑ'Ð'Ð'Ô
(×
:Ò
:¸1À"Ð
:Ñ
EÔ
E€CØ
ˆcÐ'�S”Y˜r”] aÑ'Ð'Ð'Ô
(×
:Ò
:¸1À"Ð
:Ñ
EÔ
E€Cð ”˜2”€JØ�c˜;˜J˜;Ð&Ô'¨¨3°
°°Ð+;Ô)<ˆ6€EØ�c˜;˜J˜;Ð&Ô'¨¨3°
°°Ð+;Ô)<ˆ6€Eð �s‰{�{¨5Ñ1Ô1°CÑ7Ñ8€GØ�s‰{�{¨5Ñ1Ô1°CÑ7Ñ8€Gõ Œi˜ &Ð)¨rÐ2Ñ2Ô2€GÝŒi˜ &Ð)¨rÐ2Ñ2Ô2€GØ�GÐÐr4   c                   óÖ   ‡ — e Zd ZdZddededz  fˆ fd„Z	 	 	 ddej        de	ej        ej        f         dz  dej        dz  d	e
dz  d
ee         de	ej        ej        f         fd„Zˆ xZS )rL   z=Multi-headed attention from 'Attention Is All You Need' paperNr'   rH   c                 ó¤  •— t          ¦   «                              ¦   «          || _        || _        t	          |d|j        |j        z  ¦  «        | _        |j        |j        z  | _	        | j        dz  | _
        |j        | _        d| _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        | j        z  |j        d¬¦  «        | _        d S )Nrm   g      à¿Tr#   F)r%   r&   r'   rH   Úgetattrr*   Únum_attention_headsrm   rk   rz   rt   Úattention_dropoutÚ	is_causalr(   r)   Úattention_biasÚq_projÚk_projÚv_projÚo_projrU   s      €r3   r&   zGlm4Attention.__init__È   s8  ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒÝ ¨
°FÔ4FÈ&ÔJdÑ4dÑeÔeˆŒØ$*Ô$>À&ÔB\Ñ$\ˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒå”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”i Ô :¸T¼]Ñ JÈFÔL^ÐejÐkÑkÔkˆŒˆˆr4   r5   rZ   rV   rX   r[   r6   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 )Nr8   r   r"   ro   )ru   rt   )rg   rm   r§   Úviewr|   r¨   r©   rŸ   ÚupdaterH   r   Úget_interfacer'   Ú_attn_implementationr†   ry   r¤   rt   ri   r�   rª   )r1   r5   rZ   rV   rX   r[   Úinput_shapeÚhidden_shapeÚquery_statesr‚   rƒ   r•   r–   Úattention_interfacer…   r„   s                   r3   r>   zGlm4Attention.forwardÝ   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   ©N©NNN)r?   r@   rA   Ú__doc__r   r`   r&   rB   ra   rd   r   r   r   r>   rD   rE   s   @r3   rL   rL   Å   s÷   ø€ € € € € ØGÐGðlð l˜zð l°c¸D±jð lð lð lð lð lð lð0 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   rL   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Glm4RotaryEmbeddingÚ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defaultr¹   F)Ú
persistentÚoriginal_inv_freq)r%   r&   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr'   Úrope_parametersr»   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r1   r'   ÚdeviceÚrope_init_fnr¹   r2   s        €r3   r&   zGlm4RotaryEmbedding.__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Ur4   rÇ   ztorch.deviceÚseq_lenr6   ztorch.Tensorc                 óV  — | j         d         }| j                              dd¦  «        }t          | dd¦  «        p| j        | j        z  }t          ||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partial_rotary_factorg      ð?rm   Nr   r"   ©rw   )rÇ   rw   )rÂ   Úgetr¢   r*   r£   r`   rB   ÚarangeÚint64r€   Úfloat)	r'   rÇ   rÉ   ÚbaserÌ   rm   r:   Úattention_factorr¹   s	            r3   rÃ   z3Glm4RotaryEmbedding.compute_default_rope_parameters  sº   € ð& Ô% lÔ3ˆØ &Ô 6× :Ò :Ð;RÐTWÑ XÔ XÐÝ˜6 :¨tÑ4Ô4Ðh¸Ô8JÈfÔNhÑ8hˆÝ�(Ð2Ñ2Ñ3Ô3ˆ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   r8   r   ÚmpsÚcpuF)Údevice_typeÚenabledr"   r9   rÍ   )r¹   rÑ   rh   rg   r€   rÇ   Ú
isinstanceÚtypeÚstrr   r|   rB   r’   r•   rÄ   r–   rw   )
r1   r‹   rW   Úinv_freq_expandedÚposition_ids_expandedr×   ÚfreqsÚembr•   r–   s
             r3   r>   zGlm4RotaryEmbedding.forward9  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´   rµ   )r?   r@   rA   rB   ra   Ú__annotations__r   r&   Ústaticmethodr   r`   rd   rÑ   rÃ   Úno_gradr   r>   rD   rE   s   @r3   r¸   r¸     sù   ø€ € € € € € ØŒlÐÐÑðVð V˜zð Vð Vð Vð Vð Vð Vð  à$(Ø+/Ø"ð*ð *Ø˜TÑ!ð*à˜Ô(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ô	%ð	*ð *ð *ñ „\ð*ð> €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r4   r¸   ÚRMSNormc                   óT   ‡ — e Zd Zd	deddfˆ fd„Zdej        dej        fd„Zd„ Zˆ xZ	S )
rO   ç�íµ ÷Æ°>rK   r6   Nc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z:
        Glm4RMSNorm is equivalent to T5LayerNorm
        N)r%   r&   r(   Ú	ParameterrB   ÚonesÚweightÚvariance_epsilon)r1   r*   rK   r2   s      €r3   r&   zGlm4RMSNorm.__init__K  sD   ø€ õ 	‰Œ×ÒÑÔÐÝ”l¥5¤:¨kÑ#:Ô#:Ñ;Ô;ˆŒØ #ˆÔÐÐr4   r5   c                 ó  — |j         }|                     t          j        ¦  «        }|                     d¦  «                             dd¬¦  «        }|t          j        || j        z   ¦  «        z  }| j        |                     |¦  «        z  S )Nr"   r8   T)Úkeepdim)	rw   r€   rB   r   ÚpowÚmeanÚrsqrtrê   ré   )r1   r5   Úinput_dtypeÚvariances       r3   r>   zGlm4RMSNorm.forwardS  s|   € Ø#Ô)ˆØ%×(Ò(­¬Ñ7Ô7ˆØ ×$Ò$ QÑ'Ô'×,Ò,¨R¸Ð,Ñ>Ô>ˆØ%­¬°H¸tÔ?TÑ4TÑ(UÔ(UÑUˆØŒ{˜]×-Ò-¨kÑ:Ô:Ñ:Ð:r4   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)rd   ré   rg   rê   )r1   s    r3   Ú
extra_reprzGlm4RMSNorm.extra_reprZ  s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr4   )rå   )
r?   r@   rA   rÑ   r&   rB   ra   r>   ró   rD   rE   s   @r3   rO   rO   I  sŒ   ø€ € € € € ð$ð $¨ð $¸$ð $ð $ð $ð $ð $ð $ð; U¤\ð ;°e´lð ;ð ;ð ;ð ;ðJð Jð Jð Jð Jð Jð Jr4   rO   c                   óL   — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZdS )ÚGlm4PreTrainedModelr'   ÚmodelTrG   rX   )r5   Ú
attentionsN)r?   r@   rA   r   rà   Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendrG   rL   Ú_can_record_outputsr]   r4   r3   rõ   rõ   ^  sl   € € € € € € àÐÐÑØÐØ&*Ð#Ø+Ð,ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà)Ø#ðð ÐÐÐr4   rõ   c                   óâ   ‡ — e Zd Zdefˆ fd„Zeee	 	 	 	 	 	 ddej	        dz  dej
        dz  dej	        dz  dedz  dej        dz  d	edz  d
ee         defd„¦   «         ¦   «         ¦   «         Zˆ xZS )Ú	Glm4Modelr'   c                 óÞ  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ‰j        ¬¦  «        | _        t!          ‰¬¦  «        | _        d| _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS r]   )rG   )Ú.0rH   r'   s     €r3   ú
<listcomp>z&Glm4Model.__init__.<locals>.<listcomp>z  s$   ø€ ÐbÐbÐb°YÕ˜f iÑ0Ô0ÐbÐbÐbr4   rJ   ©r'   F)r%   r&   Úpad_token_idÚpadding_idxÚ
vocab_sizer(   Ú	Embeddingr*   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersrO   rP   Únormr¸   Ú
rotary_embÚgradient_checkpointingÚ	post_initr0   s    `€r3   r&   zGlm4Model.__init__s  sÔ   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØbÐbÐbÐbÅ%ÈÔH`ÑBaÔBaÐbÑbÔbñ
ô 
ˆŒõ   Ô 2¸Ô8KÐLÑLÔLˆŒ	Ý-°VÐ<Ñ<Ô<ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr4   NÚ	input_idsrV   rW   rX   Úinputs_embedsrY   r[   r6   c           
      óH  — |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }t          | j        ||||¬¦  «        }	|}
|                      |
|¬¦  «        }| j        d | j        j        …         D ]} ||
f|	||||dœ|¤Ž}
Œ|                      |
¦  «        }
t          |
|¬	¦  «        S )
Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )rÇ   )r'   r  rV   rX   rW   )rW   )rV   rZ   rW   rX   rY   )Úlast_hidden_staterX   )Ú
ValueErrorr  r   r'   Úget_seq_lengthrB   rÏ   rg   rÇ   r�   r   r  r  r  r  r   )r1   r  rV   rW   rX   r  rY   r[   Úpast_seen_tokensÚcausal_maskr5   rZ   Údecoder_layers                r3   r>   zGlm4Model.forwardƒ  sŠ  € ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàÐ Ø*.×*;Ò*;¸IÑ*FÔ*FˆMàð 	?˜Ð0Ý*°$´+Ð>Ñ>Ô>ˆOàÐØCRÐC^˜×=Ò=Ñ?Ô?Ð?ÐdeÐÝ œ<¨Ô(;¸AÔ(>À}ÔG[Ð\Ñ\Ô\Ð_oÑoˆLØ'×1Ò1°!Ñ4Ô4ˆLå(Ø”;Ø'Ø)Ø+Ø%ð
ñ 
ô 
ˆð &ˆØ"Ÿošo¨mÈ,˜oÑWÔWÐà!œ[Ð)H¨4¬;Ô+HÐ)HÔIð 		ð 		ˆMØ)˜MØðà*Ø$7Ø)Ø /Ø#ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝ&Ø+Ø+ð
ñ 
ô 
ð 	
r4   )NNNNNN)r?   r@   rA   r   r&   r   r   r   rB   rb   ra   r   rC   rc   r   r   r   r>   rD   rE   s   @r3   r  r  q  s  ø€ € € € € ð˜zð ð ð ð ð ð ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð2
ð 2
àÔ# dÑ*ð2
ð œ tÑ+ð2
ð Ô&¨Ñ-ð	2
ð
  ™ð2
ð Ô(¨4Ñ/ð2
ð ˜$‘;ð2
ð Ð+Ô,ð2
ð 
!ð2
ð 2
ð 2
ñ „^ñ „_ñ  Ôð2
ð 2
ð 2
ð 2
ð 2
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ez  fd„¦   «         ¦   «         Zˆ xZS )ÚGlm4ForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr5   Úlogitsc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S )NFr#   )
r%   r&   r  rö   r  r(   r)   r*   r!  r  r0   s     €r3   r&   zGlm4ForCausalLM.__init__Á  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r4   Nr   r  rV   rW   rX   r  ÚlabelsrY   Úlogits_to_keepr[   r6   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 )ah  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

        Example:

        ```python
        >>> from transformers import AutoTokenizer, Glm4ForCausalLM

        >>> model = Glm4ForCausalLM.from_pretrained("THUDM/GLM-4-9B-0414")
        >>> tokenizer = AutoTokenizer.from_pretrained("THUDM/GLM-4-9B-0414")

        >>> prompt = "Hey, are you conscious? Can you talk to me?"
        >>> inputs = tokenizer(prompt, return_tensors="pt")

        >>> # Generate
        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
        ```)r  rV   rW   rX   r  rY   N)r#  r%  r  )Úlossr#  rX   r5   r÷   r]   )rö   r  rÙ   r`   Úslicer!  Úloss_functionr'   r  r   rX   r5   r÷   )r1   r  rV   rW   rX   r  r%  rY   r&  r[   Úoutputsr5   Úslice_indicesr#  r(  s                  r3   r>   zGlm4ForCausalLM.forwardÊ  sõ   € ðH ,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@   rA   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr&   r   r   rB   rb   ra   r   rC   rc   r`   r   r   rd   r   r>   rD   rE   s   @r3   r   r   »  sQ  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;
ð ;
àÔ# dÑ*ð;
ð œ tÑ+ð;
ð Ô&¨Ñ-ð	;
ð
  ™ð;
ð Ô(¨4Ñ/ð;
ð Ô  4Ñ'ð;
ð ˜$‘;ð;
ð ˜eœlÑ*ð;
ð Ð+Ô,ð;
ð 
Ð'Ñ	'ð;
ð ;
ð ;
ñ „^ñ Ôð;
ð ;
ð ;
ð ;
ð ;
r4   r   c                   ó   — e Zd ZdS )ÚGlm4ForSequenceClassificationN©r?   r@   rA   r]   r4   r3   r1  r1  
  ó   € € € € € Ø€Dr4   r1  c                   ó   — e Zd ZdS )ÚGlm4ForTokenClassificationNr2  r]   r4   r3   r5  r5    r3  r4   r5  )rõ   r  r   r1  r5  )ro   )r   )AÚcollections.abcr   Útypingr   rB   Útorch.nnr(   Úactivationsr   Úcache_utilsr   r   Ú
generationr	   Úintegrationsr
   Úmasking_utilsr   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   r   r   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_glm4r   ÚModuler    rG   ra   r`   rn   rÑ   r†   rŽ   rŸ   rL   r¸   rO   rõ   r  r   r1  r5  Ú__all__r]   r4   r3   ú<module>rJ     s§  ðð, %Ð $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 .Ð .Ð .Ø )Ð )Ð )Ð )Ð )Ð )Ø 7Ð 7Ð 7Ð 7Ð 7Ð 7Ø /Ð /Ð /Ð /Ð /Ð /Ø 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 *Ð *Ð *Ð *Ð *Ð *ð)ð )ð )ð )ð )ˆbŒiñ )ô )ð )ð$+ð +ð +ð +ð +Ð1ñ +ô +ð +ð\	U˜Uœ\ð 	U°#ð 	U¸%¼,ð 	Uð 	Uð 	Uð 	Uð& ð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð ð%ð ð%ð Ð'Ô(ð%ð %ð %ð %ð26ð 6ð 6ð%ð %ð %ð %ðP>)ð >)ð >)ð >)ð >)�B”Iñ >)ô >)ð >)ðB@<ð @<ð @<ð @<ð @<˜"œ)ñ @<ô @<ð @<ðF Ð˜YÑ'Ô'ðJð Jð Jð Jð J�"”)ñ Jô Jñ (Ô'ðJð( ðð ð ð ð ˜/ñ ô ñ „ðð$ ðF
ð F
ð F
ð F
ð F
Ð#ñ F
ô F
ñ „ðF
ðR ðK
ð K
ð K
ð K
ð K
Ð)¨?ñ K
ô K
ñ „ðK
ð\	ð 	ð 	ð 	ð 	Ð$DÐFYñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð!>Ð@Sñ 	ô 	ð 	ðð ð €€€r4   