
    hV                     T   d dl mZmZ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( ddl)m*Z* ddl+m,Z,  G d dejZ                        Z. G d de      Z/dej`                  de1dej`                  fdZ2	 d9dejZ                  dej`                  dej`                  dej`                  d eej`                     d!e3d"e3d#e"e$   fd$Z4d% Z5d:d&Z6 G d' d(ejZ                        Z7 ed)       G d* d+ejZ                               Z8 G d, d-ejZ                        Z9e% G d. d/e              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);    )CallableOptionalUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)FlashAttentionKwargs) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)deprecate_kwarg)check_model_inputs   )
Glm4Configc                   V     e Zd Z fdZdej
                  dej
                  fdZ xZS )Glm4MLPc                 *   t         |           || _        t        j                  |j
                  d|j                  z  d      | _        t        j                  |j                  |j
                  d      | _        t        |j                     | _        y )N   Fbias)super__init__confignnLinearhidden_sizeintermediate_sizegate_up_proj	down_projr   
hidden_actactivation_fnselfr'   	__class__s     d/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/glm4/modeling_glm4.pyr&   zGlm4MLP.__init__1   sp    IIf&8&8!f>V>V:V]bc6#;#;V=O=OV[\#F$5$56    hidden_statesreturnc                     | j                  |      }|j                  dd      \  }}|| j                  |      z  }| j                  |      S )Nr"   dim)r,   chunkr/   r-   )r1   r5   	up_statesgates       r3   forwardzGlm4MLP.forward9   sL    %%m4	#//!/4i 2 24 88	~~i((r4   )__name__
__module____qualname__r&   torchFloatTensorr>   __classcell__r2   s   @r3   r    r    0   s'    7)U%6%6 )5;L;L )r4   r    c                       e Zd Zdedef fdZ eddd      	 	 	 	 	 	 ddej                  d	e	ej                     d
e	ej                     de	e   de	e   de	ej                     de	eej                  ej                  f      dee   deej                   e	eej                   ej                   f      f   fd       Z xZS )Glm4DecoderLayerr'   	layer_idxc                    t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        t        |j                  |j                        | _        t        |j                  |j                        | _        y )N)r'   rH   eps)r%   r&   r*   Glm4Attention	self_attnr    mlpGlm4RMSNormrms_norm_epsinput_layernormpost_attention_layernormpost_self_attn_layernormpost_mlp_layernormr1   r'   rH   r2   s      r3   r&   zGlm4DecoderLayer.__init__C   s    !--&f	J6?*6+=+=6CVCVW(3F4F4FFL_L_(`%(3F4F4FFL_L_(`%"-f.@.@fFYFY"Zr4   past_key_valuepast_key_values4.58new_nameversionr5   attention_maskposition_ids	use_cachecache_positionposition_embeddingskwargsr6   c                    |}	| j                  |      } | j                  d|||||||d|\  }}
| j                  |      }|	|z   }|}	| j                  |      }| j	                  |      }| j                  |      }|	|z   }|S )N)r5   r\   r]   rW   r^   r_   r`    )rQ   rM   rS   rR   rN   rT   )r1   r5   r\   r]   rW   r^   r_   r`   ra   residual_s              r3   r>   zGlm4DecoderLayer.forwardN   s     !,,];)4>> 	
')%+) 3	
 	
q 55mD =0 55mD///> =0r4   )NNNFNN)r?   r@   rA   r   intr&   r   rB   Tensorr   
LongTensorr   booltupler   r   rC   r>   rD   rE   s   @r3   rG   rG   B   s   	[z 	[c 	[ %0A6R 2637+/$)59KO!||! !.! u//0	!
 "%! D>! !!1!12! &eELL%,,,F&GH! -.! 
u  (51B1BEDUDU1U+V"WW	X! S!r4   rG   r5   n_repr6   c                     | j                   \  }}}}|dk(  r| S | dddddddddf   j                  |||||      } | j                  |||z  ||      S )z
    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)shapeexpandreshape)r5   rk   batchnum_key_value_headsslenhead_dims         r3   	repeat_kvrt   s   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr4   modulequerykeyvaluer\   scalingdropoutra   c                 T   t        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
|#|d d d d d d d |j
                  d   f   }|
|z   }
t        j                  j                  |
dt        j                        j                  |j                        }
t        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )Nr"   r   r8   )r:   dtype)ptrainingr   )rt   num_key_value_groupsrB   matmul	transposerm   r(   
functionalsoftmaxfloat32tor}   rz   r   
contiguous)ru   rv   rw   rx   r\   ry   rz   ra   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r3   eager_attention_forwardr      s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#k1==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r4   c                 |    | ddddf   }| ddddf   }t        j                  | |fd      j                  d      S )	z*Rotates half the hidden dims of the input..r   Nr"   r   r8   r9   r|   )rB   stackflatten)xx1x2s      r3   rotate_halfr      sJ    	
319B	
319B;;Ryb)11"55r4   c                    |j                  |      }|j                  |      }|dd|j                  d   dz  f   j                  dd      }|dd|j                  d   dz  f   j                  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.
        position_ids (`torch.Tensor`, *optional*):
            Deprecated and unused.
        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   )	unsqueezerm   repeat_interleaver   rB   cat)qkcossinr]   unsqueeze_dim
rotary_dimq_rotq_passk_rotk_passq_embedk_embeds                r3   apply_rotary_pos_embr      sD   ( --
&C
--
&C c'SYYr]a'''
(
:
:1"
:
EC
c'SYYr]a'''
(
:
:1"
:
EC 2Jc;J;&'3
+;)<6Ec;J;&'3
+;)<6E s{{51C78Gs{{51C78G ii&)r2Gii&)r2GGr4   c                   2    e Zd ZdZddedee   f fdZ eddd      	 	 dd	e	j                  d
ee	j                  e	j                  f   dee	j                     dee   dee	j                     dee   dee	j                  e	j                  f   fd       Z xZS )rL   z=Multi-headed attention from 'Attention Is All You Need' paperr'   rH   c                 P   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      | _        y )Nrs   g      Tr#   F)r%   r&   r'   rH   getattrr*   num_attention_headsrs   rq   r   ry   attention_dropout	is_causalr(   r)   attention_biasq_projk_projv_projo_projrU   s      r3   r&   zGlm4Attention.__init__   sD   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JFL^L^ejkr4   rV   rW   rX   rY   r5   r`   r\   r_   ra   r6   c                 4   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                  sdn| j                  | j                   d|\  }} |j"                  g |d j%                         }| j'                  |      }||fS )Nr8   r   r"   )r   r   r_   eager        )rz   ry   )rm   rs   r   viewr   r   r   r   updaterH   r   r'   _attn_implementationr   r   r   ry   ro   r   r   )r1   r5   r`   r\   rW   r_   ra   input_shapehidden_shapequery_statesr   r   r   r   cache_kwargsattention_interfacer   r   s                     r3   r>   zGlm4Attention.forward   s    $))#2.88b8$--8{{=166|DNNqRST[[/44\BLLQPQR
{{=166|DNNqRST&S#7jRUWZ#[ j&#&snUL'6'='=j,X\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r4   N)NN)r?   r@   rA   __doc__r   r   rf   r&   r   rB   rg   rj   r   rh   r   r   r>   rD   rE   s   @r3   rL   rL      s    Glz lhsm l* %0A6R ,059))||)) #5<<#=>)) !.	))
 "%)) !!1!12)) +,)) 
u||U\\)	*)) S))r4   rL   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )rO   c                     t         |           t        j                  t	        j
                  |            | _        || _        y)z:
        Glm4RMSNorm is equivalent to T5LayerNorm
        N)r%   r&   r(   	ParameterrB   onesweightvariance_epsilon)r1   r*   rK   r2   s      r3   r&   zGlm4RMSNorm.__init__  s1     	ll5::k#:; #r4   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )Nr"   r8   T)keepdim)	r}   r   rB   r   powmeanrsqrtr   r   )r1   r5   input_dtypevariances       r3   r>   zGlm4RMSNorm.forward  sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r4   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)rj   r   rm   r   )r1   s    r3   
extra_reprzGlm4RMSNorm.extra_repr   s*    ))*+6$2G2G1HIIr4   )gư>)r?   r@   rA   r&   r>   r   rD   rE   s   @r3   rO   rO     s    $;Jr4   rO   c                   ~     e Zd ZU ej                  ed<   ddef fdZ ej                         e	d               Z
 xZS )Glm4RotaryEmbeddinginv_freqr'   c                    t         |           t        |d      rUt        |j                  t
              r;|j                  j                  d|j                  j                  d            | _        nd| _        |j                  | _	        |j                  | _
        || _        t        | j                     | _        | j                  | j                  |      \  }| _        | j                  d|d       | j                   | _        y )Nrope_scaling	rope_typetypedefaultr   F)
persistent)r%   r&   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr'   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r1   r'   devicer   r2   s       r3   r&   zGlm4RotaryEmbedding.__init__'  s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r4   c                 b   | 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        j                  |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   AxY w)Nr   r8   r   mpscpuF)device_typeenabledr"   r9   )r}   )r   floatrn   rm   r   r   r   r   strrB   autocastr   r   r   r   r   r}   )
r1   r   r]   inv_freq_expandedposition_ids_expandedr   freqsembr   r   s
             r3   r>   zGlm4RotaryEmbedding.forward8  sV    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E!((--[`J`ahhmmfk^^UC 	5&,,.1F1L1L1NNYYZ[]^_E))UEN3C'')d444C'')d444C		5 vvAGGv$cff177f&;;;	5 	5s    BF%%F.r   )r?   r@   rA   rB   rg   __annotations__r   r&   no_gradr   r>   rD   rE   s   @r3   r   r   $  s=    ll/z /" U]]_<  <r4   r   c                   J    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Zy)Glm4PreTrainedModelr'   modelTrG   rW   )r5   
attentionsN)r?   r@   rA   r   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendrG   rL   _can_record_outputsrc   r4   r3   r   r   H  sQ    &*#+,#4"5N!"&)#r4   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej                     deej                     deej                     dee   deej                     deej                     d	ee   d
ee   defd              Z xZS )	Glm4Modelr'   c           	         t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        | j)                          y c c}w )NrJ   r'   F)r%   r&   pad_token_idpadding_idx
vocab_sizer(   	Embeddingr*   embed_tokens
ModuleListrangenum_hidden_layersrG   layersrO   rP   normr   
rotary_embgradient_checkpointing	post_initrU   s      r3   r&   zGlm4Model.__init__]  s     !.. ++LL):):F<N<NPTP`P`ammBGH`H`BabYfi0b
   2 28K8KL	-V<&+# 	 cs   D	input_idsr\   r]   rW   inputs_embedsr_   r^   ra   r6   c           
      B   |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|F||j	                         nd}	t        j                  |	|	|j                  d   z   |j                        }||j                  d      }t        | j                  |||||      }
|}| j                  ||      }| j                  d | j                  j                   D ]  } ||f|
||||d|} | j                  |      }t        ||      S )	Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )r   )r'   input_embedsr\   r_   rW   r]   )r\   r]   rW   r_   r`   )last_hidden_staterW   )
ValueErrorr  r	   r'   get_seq_lengthrB   arangerm   r   r   r   r  r  r
  r  r   )r1   r  r\   r]   rW   r  r_   r^   ra   past_seen_tokensr   r5   r`   decoder_layers                 r3   r>   zGlm4Model.forwardm  s[    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de+0<< "2]5H5H5K"KTaThTh,N )33A6L(;;&))+%
 &"oom\J![[)H4;;+H+HI 		M)*) /-$7 M		 		-0&++
 	
r4   )NNNNNNN)r?   r@   rA   r   r&   r   r   r   rB   rh   rg   r   rC   ri   r   r   r   r>   rD   rE   s   @r3   r   r   [  s    z    151537+/5959$(8
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 !!1!128
 D>8
 +,8
 
!8
  8
r4   r   c                   n    e Zd ZdgZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dde	e
j                     de	e
j                     d	e	e
j                     d
e	e   de	e
j                     de	e
j                     de	e   de	e
j                     deee
j                  f   dee   deeef   fd              Z xZS )Glm4ForCausalLMzlm_head.weightlm_headcolwise_repr5   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFr#   )
r%   r&   r   r   r  r(   r)   r*   r  r  r0   s     r3   r&   zGlm4ForCausalLM.__init__  sU     v&
 ++yy!3!3V5F5FUS 	r4   r  r\   r]   rW   r  labelsr^   r_   logits_to_keepra   r6   c
                 z    | j                   d|||||||d|
}|j                  }t        |	t              rt	        |	 d      n|	}| j                  |dd|ddf         }d}|* | j                  d||| j                  j                  d|
}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  r\   r]   rW   r  r^   r_   N)r  r   r  )lossr  rW   r5   r   rc   )r   r  r   rf   slicer  loss_functionr'   r  r   rW   r5   r   )r1   r  r\   r]   rW   r  r   r^   r_   r!  ra   outputsr5   slice_indicesr  r#  s                   r3   r>   zGlm4ForCausalLM.forward  s    J ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r4   )	NNNNNNNNr   )r?   r@   rA   _tied_weights_keys_tp_plan_pp_planr&   r   r   r   rB   rh   rg   r   rC   ri   r   rf   r   r   rj   r   r>   rD   rE   s   @r3   r  r    s;   *+=)H_-z:;H  151537+/59-1$(5934=
E,,-=
 !.=
 u//0	=

 "%=
   1 12=
 ))*=
 D>=
 !!1!12=
 c5<</0=
 +,=
 
u,,	-=
  =
r4   r  c                       e Zd Zy)Glm4ForSequenceClassificationNr?   r@   rA   rc   r4   r3   r,  r,        r4   r,  c                       e Zd Zy)Glm4ForTokenClassificationNr-  rc   r4   r3   r0  r0    r.  r4   r0  )r   r   r  r,  r0  )r   )Nr   )@typingr   r   r   rB   torch.nnr(   activationsr   cache_utilsr   r	   
generationr
   integrationsr   masking_utilsr   modeling_flash_attention_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.deprecationr   utils.genericr   configuration_glm4r   Moduler    rG   rg   rf   rt   r   r   r   r   rL   rO   r   r   r   r  r,  r0  __all__rc   r4   r3   <module>rD     s  , - ,   ! . ) 7 / B 
 P K F & I I 0 / *)bii )$.1 .b	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%46'TB)BII B)J Y'J")) J (J(!<")) !<H /  $ K
# K
 K
\ M
)? M
 M
`	$DFY 		!>@S 	r4   