
    hS                     H   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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jV                        Z,dejZ                  de.dejZ                  fdZ/	 d8dejV                  dejZ                  dejZ                  dejZ                  deejZ                     de0de0d e e"   fd!Z1d" Z2d9d#Z3 G d$ d%ejV                        Z4 ed&       G d' d(ejV                               Z5 G d) d*ejV                        Z6 G d+ d,e      Z7e# G d- d.e             Z8e# G d/ d0e8             Z9e# G d1 d2e8e             Z: G d3 d4ee8      Z; G d5 d6ee8      Z<g d7Z=y):    )CallableOptionalUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask) 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   )	GlmConfigc                   V     e Zd Z fdZdej
                  dej
                  fdZ xZS )GlmMLPc                 *   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     b/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/glm/modeling_glm.pyr%   zGlmMLP.__init__0   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,   )r0   r4   	up_statesgates       r2   forwardzGlmMLP.forward8   sL    %%m4	#//!/4i 2 24 88	~~i((r3   )__name__
__module____qualname__r%   torchFloatTensorr=   __classcell__r1   s   @r2   r   r   /   s'    7)U%6%6 )5;L;L )r3   r   r4   n_repr5   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)r4   rE   batchnum_key_value_headsslenhead_dims         r2   	repeat_kvrN   A   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr3   modulequerykeyvalueattention_maskscalingdropoutkwargsc                 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   r7   )r9   dtype)ptrainingr   )rN   num_key_value_groupsrA   matmul	transposerG   r'   
functionalsoftmaxfloat32torY   rU   r[   
contiguous)rO   rP   rQ   rR   rS   rT   rU   rV   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r2   eager_attention_forwardri   M   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$$r3   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   r7   r8   rX   )rA   stackflatten)xx1x2s      r2   rotate_halfrp   g   sJ    	
319B	
319B;;Ryb)11"55r3   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.
    .Nr7   r!   r8   )	unsqueezerG   repeat_interleaverp   rA   cat)qkcossinposition_idsunsqueeze_dim
rotary_dimq_rotq_passk_rotk_passq_embedk_embeds                r2   apply_rotary_pos_embr   n   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r3   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 )GlmAttentionz=Multi-headed attention from 'Attention Is All You Need' paperr&   	layer_idxc                 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 )NrM   g      Tr"   F)r$   r%   r&   r   getattrr)   num_attention_headsrM   rK   r\   rT   attention_dropout	is_causalr'   r(   attention_biasq_projk_projv_projo_projr0   r&   r   r1   s      r2   r%   zGlmAttention.__init__   sD   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JFL^L^ejkr3   past_key_valuepast_key_values4.58new_nameversionr4   position_embeddingsrS   cache_positionrV   r5   c                 4   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                  sdn| j                  | j                   d|\  }} |j"                  g |d j%                         }| j'                  |      }||fS )Nr7   r   r!   )rx   rw   r   eager        )rU   rT   )rG   rM   r   viewr^   r   r   r   updater   ri   r&   _attn_implementationr   r[   r   rT   rI   rc   r   )r0   r4   r   rS   r   r   rV   input_shapehidden_shapequery_statesrd   re   rw   rx   cache_kwargsattention_interfacerh   rf   s                     r2   r=   zGlmAttention.forward   s    $))#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$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r3   N)NN)r>   r?   r@   __doc__r   r   intr%   r   rA   Tensortupler   
LongTensorr   r   r=   rC   rD   s   @r2   r   r      s    Gly lXc] l* %0A6R ,059))||)) #5<<#=>)) !.	))
 "%)) !!1!12)) +,)) 
u||U\\)	*)) S))r3   r   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )
GlmRMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z9
        GlmRMSNorm is equivalent to T5LayerNorm
        N)r$   r%   r'   	ParameterrA   onesweightvariance_epsilon)r0   r)   epsr1   s      r2   r%   zGlmRMSNorm.__init__   s1     	ll5::k#:; #r3   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )Nr!   r7   T)keepdim)	rY   rb   rA   ra   powmeanrsqrtr   r   )r0   r4   input_dtypevariances       r2   r=   zGlmRMSNorm.forward   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r3   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)r   r   rG   r   )r0   s    r2   
extra_reprzGlmRMSNorm.extra_repr   s*    ))*+6$2G2G1HIIr3   )gư>)r>   r?   r@   r%   r=   r   rC   rD   s   @r2   r   r      s    $;Jr3   r   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 )GlmRotaryEmbedding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)r0   r&   devicer   r1   s       r2   r%   zGlmRotaryEmbedding.__init__   s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r3   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   r7   r   mpscpuF)device_typeenabledr!   r8   )rY   )r   floatrH   rG   rb   r   r   r   strrA   autocastr^   rt   rw   r   rx   rY   )
r0   rm   ry   inv_freq_expandedposition_ids_expandedr   freqsembrw   rx   s
             r2   r=   zGlmRotaryEmbedding.forward  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?   r@   rA   r   __annotations__r   r%   no_gradr   r=   rC   rD   s   @r2   r   r      s=    ll/y /" U]]_<  <r3   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j                  fd       Z xZS )GlmDecoderLayerr&   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)r&   r   r   )r$   r%   r)   r   	self_attnr   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   s      r2   r%   zGlmDecoderLayer.__init__  sk    !--%VyI&>)&*<*<&BUBUV(263E3E6K^K^(_%r3   r   r   r   r   r4   rS   ry   	use_cacher   r   rV   r5   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r4   rS   ry   r   r   r   r    )r   r   r   r   )r0   r4   rS   ry   r   r   r   r   rV   residual_s              r2   r=   zGlmDecoderLayer.forward!  s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r3   )NNNFNN)r>   r?   r@   r   r   r%   r   rA   r   r   r   r   boolr   r   r   r=   rC   rD   s   @r2   r   r     s    `y `S ` %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 Sr3   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)GlmPreTrainedModelr&   modelTr   r   )r4   
attentionsN)r>   r?   r@   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_backendr   r   _can_record_outputsr   r3   r2   r   r   D  sQ    &*#*+#4"5N!"&("r3   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 )GlmModelr&   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 )Nr   r&   F)r$   r%   pad_token_idpadding_idx
vocab_sizer'   	Embeddingr)   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normr   
rotary_embgradient_checkpointing	post_initr   s      r2   r%   zGlmModel.__init__Y  s     !.. ++LL):):F<N<NPTP`P`ammAFvG_G_A`aI_VY/a
 v11v7J7JK	,F;&+# 	 bs   D	input_idsrS   ry   r   inputs_embedsr   r   rV   r5   c           
      B   |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|F||j	                         nd}	t        j                  |	|	|j                  d   z   |j                        }||j                  d      }t        | j                  |||||      }
|}| j                  ||      }| j                  d | j                  j                   D ]  } ||f|
||||d|} | j                  |      }t        ||      S )	Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )r   )r&   input_embedsrS   r   r   ry   )rS   ry   r   r   r   )last_hidden_stater   )
ValueErrorr  r	   r&   get_seq_lengthrA   arangerG   r   rr   r   r
  r  r  r	  r   )r0   r  rS   ry   r   r  r   r   rV   past_seen_tokensrg   r4   r   decoder_layers                 r2   r=   zGlmModel.forwardi  s[    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de+0<< "2]5H5H5K"KTaThTh,N )33A6L(;;&))+%
 &"oom\J![[)H4;;+H+HI 		M)*) /-$7 M		 		-0&++
 	
r3   )NNNNNNN)r>   r?   r@   r   r%   r   r   r   rA   r   r   r   rB   r   r   r   r   r=   rC   rD   s   @r2   r   r   W  s    y    151537+/5959$(8
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 !!1!128
 D>8
 +,8
 
!8
  8
r3   r   c                   d    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fd              Z xZS )GlmForCausalLMzlm_head.weightlm_headcolwise_repr4   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFr"   )
r$   r%   r   r   r  r'   r(   r)   r  r  r/   s     r2   r%   zGlmForCausalLM.__init__  sU     f%
 ++yy!3!3V5F5FUS 	r3   r  rS   ry   r   r  labelsr   r   logits_to_keeprV   r5   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 )a  
        Example:

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

        >>> model = GlmForCausalLM.from_pretrained("meta-glm/Glm-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-glm/Glm-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."
        ```)r  rS   ry   r   r  r   r   N)r  r  r  )lossr  r   r4   r   r   )r   r  r   r   slicer  loss_functionr&   r  r   r   r4   r   )r0   r  rS   ry   r   r  r  r   r   r  rV   outputsr4   slice_indicesr  r   s                   r2   r=   zGlmForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r3   )	NNNNNNNNr   )r>   r?   r@   _tied_weights_keys_tp_plan_pp_planr%   r   r   r   rA   r   r   r   rB   r   r   r   r   r   r   r=   rC   rD   s   @r2   r  r    s0   *+=)H_-z:;H  151537+/59-1$(59348
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 ))*8
 D>8
 !!1!128
 c5<</08
 +,8
 
 8
  8
r3   r  c                       e Zd Zy)GlmForSequenceClassificationNr>   r?   r@   r   r3   r2   r)  r)        r3   r)  c                       e Zd Zy)GlmForTokenClassificationNr*  r   r3   r2   r-  r-    r+  r3   r-  )r   r   r  r)  r-  )r   )Nr   )>typingr   r   r   rA   torch.nnr'   activationsr   cache_utilsr   r	   
generationr
   integrationsr   masking_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_glmr   Moduler   r   r   rN   r   ri   rp   r   r   r   r   r   r   r   r  r)  r-  __all__r   r3   r2   <module>r@     s  , - ,   ! . ) 7 / 
 P K F & I I 0 / ()RYY )$	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%46'TB)299 B)J Y'J J (J(!< !<H+0 +\   $ K
! K
 K
\ H
' H
 H
V	#CEW 		 =?Q 	r3   