
     `iS                     B   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j+                  Z,dej-        de.dej-        fdZ/	 d9dej+        dej-        dej-        dej-        deej-                 de0d e0d!e e"         fd"Z1d# Z2d:d$Z3 G d% d&ej+                  Z4 ed'           G d( d)ej+                              Z5 G d* d+ej+                  Z6 G d, d-e          Z7e# G d. d/e                      Z8e# G d0 d1e8                      Z9e# G d2 d3e8e                      Z: G d4 d5ee8          Z; G d6 d7ee8          Z<g d8Z=dS );    )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                   B     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
                 | _        d S )N   Fbias)super__init__confignnLinearhidden_sizeintermediate_sizegate_up_proj	down_projr   
hidden_actactivation_fnselfr&   	__class__s     x/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/glm/modeling_glm.pyr%   zGlmMLP.__init__0   sz    If&8!f>V:V]bccc6#;V=OV[\\\#F$56    hidden_statesreturnc                     |                      |          }|                    dd          \  }}||                     |          z  }|                     |          S )Nr!   dim)r+   chunkr.   r,   )r0   r4   	up_statesgates       r2   forwardzGlmMLP.forward8   sX    %%m44	#//!/44i 2 24 8 88	~~i(((r3   )__name__
__module____qualname__r%   torchFloatTensorr=   __classcell__r1   s   @r2   r   r   /   s`        7 7 7 7 7)U%6 )5;L ) ) ) ) ) ) ) )r3   r   r4   n_repr5   c                     | j         \  }}}}|dk    r| S | dddddddddf                             |||||          } |                     |||z  ||          S )z
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r   N)shapeexpandreshape)r4   rE   batchnum_key_value_headsslenhead_dims         r2   	repeat_kvrN   A   s    
 2?1D.Ehzz!!!!QQQaaa"23::5BUW\^bdlmmM  (;e(CT8TTTr3           modulequerykeyvalueattention_maskscalingdropoutkwargsc                 R   t          || j                  }t          || j                  }	t          j        ||                    dd                    |z  }
|$|d d d d d d d |j        d         f         }|
|z   }
t          j                            |
dt          j	                  
                    |j                  }
t          j                            |
|| j                  }
t          j        |
|	          }|                    dd                                          }||
fS )Nr!   r   r7   )r9   dtype)ptrainingr   )rN   num_key_value_groupsrA   matmul	transposerG   r'   
functionalsoftmaxfloat32torZ   rV   r\   
contiguous)rP   rQ   rR   rS   rT   rU   rV   rW   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r2   eager_attention_forwardrj   M   s    3 ;<<JUF$?@@L<z';';Aq'A'ABBWLL!$QQQ111.D
0@0D.D%DE#k1=((2U](SSVVW\WbccL=((6?([[L,|\::K''1--88::K$$r3   c                     | 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   r7   r8   rY   )rA   stackflatten)xx1x2s      r2   rotate_halfrq   g   sQ    	
319B	
319B;Ryb)))11"555r3   c                 T   |                     |          }|                     |          }|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.
        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_interleaverq   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   s\   ( --
&
&C
--
&
&C c'SYr]a'''
(
:
:1"
:
E
EC
c'SYr]a'''
(
:
:1"
:
E
EC 2Jc;J;&'3
+;)<6Ec;J;&'3
+;)<6E s{{511C78Gs{{511C78G i&)r222Gi&)r222GGr3   c                   "    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' paperNr&   	layer_idxc                    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      Tr"   F)r$   r%   r&   r   getattrr)   num_attention_headsrM   rK   r]   rU   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__   s8   "
F4F&Jd4dee$*$>&B\$\!}d*!'!9i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i :T] JFL^ejkkkr3   past_key_valuepast_key_values4.58new_nameversionr4   position_embeddingsrT   cache_positionrW   r5   c                 D   |j         d d         }g |d| j        R }|                     |                              |                              dd          }	|                     |                              |                              dd          }
|                     |                              |                              dd          }|\  }}t          |	|
||          \  }	}
|&|||d}|                    |
|| j	        |          \  }
}t          }| j        j        dk    rt          | j        j                 } || |	|
||f| j        sdn| j        | j        d|\  }} |j        g |dR                                  }|                     |          }||fS )Nr7   r   r!   )ry   rx   r   eagerrO   )rV   rU   )rG   rM   r   viewr_   r   r   r   updater   rj   r&   _attn_implementationr   r\   r   rU   rI   rd   r   )r0   r4   r   rT   r   r   rW   input_shapehidden_shapequery_statesre   rf   rx   ry   cache_kwargsattention_interfaceri   rg   s                     r2   r=   zGlmAttention.forward   s    $)#2#.88b8$-88{{=1166|DDNNqRSTT[[//44\BBLLQPQRR
{{=1166|DDNNqRSTT&S#7jRUWZ#[#[ j&#&snUUL'6'='=j,X\Xfht'u'u$J(?;+w66"9$+:Z"[$7$7	%
  $}HCC$2HL	%
 	%
 	%
 	%
!\ *k);;;;;;FFHHkk+..L((r3   N)NN)r>   r?   r@   __doc__r   r   intr%   r   rA   Tensortupler   
LongTensorr   r   r=   rC   rD   s   @r2   r   r      s        GGl ly lXc] l l l l l l* _%0A6RRR ,059)) ))|)) #5<#=>)) !.	))
 "%)) !!12)) +,)) 
u|U\)	*)) )) )) SR)) )) )) )) ))r3   r   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )
GlmRMSNormư>c                     t                                                       t          j        t	          j        |                    | _        || _        dS )z9
        GlmRMSNorm is equivalent to T5LayerNorm
        N)r$   r%   r'   	ParameterrA   onesweightvariance_epsilon)r0   r)   epsr1   s      r2   r%   zGlmRMSNorm.__init__   sD     	l5:k#:#:;; #r3   c                    |j         }|                    t          j                  }|                    d                              dd          }|t          j        || j        z             z  }| j        |                    |          z  S )Nr!   r7   T)keepdim)	rZ   rc   rA   rb   powmeanrsqrtr   r   )r0   r4   input_dtypevariances       r2   r=   zGlmRMSNorm.forward   s|    #)%((77 $$Q'',,R,>>%Ht?T4T(U(UU{]--k::::r3   c                 H    t          | j        j                   d| j         S )Nz, eps=)r   r   rG   r   )r0   s    r2   
extra_reprzGlmRMSNorm.extra_repr   s&    )**II$2GIIIr3   )r   )r>   r?   r@   r%   r=   r   rC   rD   s   @r2   r   r      sb        $ $ $ $ $ $; ; ;J J J J J J Jr3   r   c                   |     e Zd ZU ej        ed<   ddef fdZ ej                    e	d                         Z
 xZS )GlmRotaryEmbeddinginv_freqNr&   c                    t                                                       t          |d          rSt          |j        t
                    r9|j                            d|j                            d                    | _        nd| _        |j        | _	        |j        | _
        || _        t          | j                 | _        |                     | j        |          \  }| _        |                     d|d           | j        | _        d S )Nrope_scaling	rope_typetypedefaultr   F)
persistent)r$   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&:Mt/T/T 	'#044[&BUBYBYZ`BaBabbDNN&DN"("@$*$B!/?+/+<+<T[&+Q+Q($(ZeDDD!%r3   c                 X   | j         d d d d f                                                             |j        d         dd                              |j                  }|d d d d d f                                         }t          |j        j        t                    r|j        j        dk    r|j        j        nd}t          j
        |d          5  |                                |                                z                      dd          }t          j        ||fd	          }|                                | j        z  }|                                | j        z  }	d d d            n# 1 swxY w Y   |                    |j        
          |	                    |j        
          fS )Nr   r7   r   mpscpuF)device_typeenabledr!   r8   )rZ   )r   floatrH   rG   rc   r   r   r   strrA   autocastr_   ru   rx   r   ry   rZ   )
r0   rn   rz   inv_freq_expandedposition_ids_expandedr   freqsembrx   ry   s
             r2   r=   zGlmRotaryEmbedding.forward  s    !M$4-8>>@@GGHZ[\H]_acdeehhijiqrr ,QQQaaaZ 8 > > @ @'1!(-'E'Ek!(-[`J`J`ahmmfk^UCCC 	5 	5&,,..1F1L1L1N1NNYYZ[]^__E)UEN333C''))d44C''))d44C		5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 	5 vvAGv$$cff17f&;&;;;s   BE++E/2E/r   )r>   r?   r@   rA   r   __annotations__r   r%   no_gradr   r=   rC   rD   s   @r2   r   r      s         l/ /y / / / / / /" U]__< <  _< < < < <r3   r   c                   4    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                 4   t                                                       |j        | _        t          ||          | _        t          |          | _        t          |j        |j                  | _	        t          |j        |j                  | _
        d S )N)r&   r   r   )r$   r%   r)   r   	self_attnr   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   s      r2   r%   zGlmDecoderLayer.__init__  s    !-%VyIII&>>)&*<&BUVVV(263E6K^(_(_(_%%%r3   r   r   r   r   NFr4   rT   rz   	use_cacher   r   rW   r5   c                     |}	|                      |          } | j        d|||||||d|\  }}
|	|z   }|}	|                     |          }|                     |          }|	|z   }|S )N)r4   rT   rz   r   r   r   r    )r   r   r   r   )r0   r4   rT   rz   r   r   r   r   rW   residual_s              r2   r=   zGlmDecoderLayer.forward!  s     !,,];;)4> 	
')%+) 3	
 	
 	
 	
q !=0 !55mDD// =0r3   )NNNFNN)r>   r?   r@   r   r   r%   r   rA   r   r   r   r   boolr   r   r   r=   rC   rD   s   @r2   r   r     s5       `y `S ` ` ` ` ` ` _%0A6RRR 2637+/$)59KO | !. u/0	
 "% D> !!12 &eEL%,,F&GH +, 
   SR    r3   r   c                   L    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dS )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  sl         &*#*+#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	        fdt          j                  D                       | _        t          j        j                  | _        t!                    | _        d| _        |                                  d S )Nc                 0    g | ]}t          |          S r   )r   ).0r   r&   s     r2   
<listcomp>z%GlmModel.__init__.<locals>.<listcomp>`  s#    aaaI_VY//aaar3   r   r&   F)r$   r%   pad_token_idpadding_idx
vocab_sizer'   	Embeddingr)   embed_tokens
ModuleListrangenum_hidden_layerslayersr   r   normr   
rotary_embgradient_checkpointing	post_initr/   s    `r2   r%   zGlmModel.__init__Y  s       !. +L):F<NPTP`aamaaaavG_A`A`aaa
 
 v1v7JKKK	,F;;;&+# 	r3   N	input_idsrT   rz   r   inputs_embedsr   r   rW   r5   c           
      N   |d u |d uz  rt          d          ||                     |          }|r|t          | j                  }|B||                                nd}	t          j        |	|	|j        d         z   |j                  }||	                    d          }t          | j        |||||          }
|}|                     ||          }| j        d | j        j                 D ]} ||f|
||||d|}|                     |          }t          ||          S )	Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )r   )r&   input_embedsrT   r   r   rz   )rT   rz   r   r   r   )last_hidden_stater   )
ValueErrorr  r	   r&   get_seq_lengthrA   arangerG   r   rs   r   r  r  r  r  r   )r0   r  rT   rz   r   r  r   r   rW   past_seen_tokensrh   r4   r   decoder_layers                 r2   r=   zGlmModel.forwardi  s    -t";< 	[YZZZ *.*;*;I*F*FM 	?0*$+>>>O!CRC^==???de+0< "2]5H5K"KTaTh, , ,N )33A66L(;&))+%
 
 
 &"oom\JJ![)H4;+H)HI 		 		M)M*) /-$7   MM 		-00&++
 
 
 	
r3   )NNNNNNN)r>   r?   r@   r   r%   r   r   r   rA   r   r   r   rB   r   r   r   r   r=   rC   rD   s   @r2   r   r   W  s       y         151537+/5959$(8
 8
E,-8
 !.8
 u/0	8

 "%8
   128
 !!128
 D>8
 +,8
 
!8
 8
 8
 ^ 8
 8
 8
 8
 8
r3   r   c                   f    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          | _        | 	                                 d S )NFr"   )
r$   r%   r   r   r  r'   r(   r)   r  r  r/   s     r2   r%   zGlmForCausalLM.__init__  sj       f%%
 +y!3V5FUSSS 	r3   Nr   r  rT   rz   r   r  labelsr   r   logits_to_keeprW   r5   c
                 R    | j         d|||||||d|
}|j        }t          |	t                    rt	          |	 d          n|	}|                     |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  rT   rz   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  rT   rz   r   r  r!  r   r   r"  rW   outputsr4   slice_indicesr  r$  s                   r2   r=   zGlmForCausalLM.forward  s    @ ,64: 	,
)%+')	,
 	,
 	,
 	,
  18B>SV8W8Wk~ot444]kmAAA}aaa,?@AA%4%pVFt{OeppioppD%#3!/)
 
 
 	
r3   )	NNNNNNNNr   )r>   r?   r@   _tied_weights_keys_tp_plan_pp_planr%   r   r   r   rA   r   r   r   rB   r   r   r   r   r   r   r=   rC   rD   s   @r2   r  r    sa       *+=)H_-z:;H      151537+/59-1$(59348
 8
E,-8
 !.8
 u/0	8

 "%8
   128
 )*8
 D>8
 !!128
 c5</08
 +,8
 
 8
 8
 8
 ^ 8
 8
 8
 8
 8
r3   r  c                       e Zd ZdS )GlmForSequenceClassificationNr>   r?   r@   r   r3   r2   r-  r-            Dr3   r-  c                       e Zd ZdS )GlmForTokenClassificationNr.  r   r3   r2   r1  r1    r/  r3   r1  )r   r   r  r-  r1  )rO   )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   rj   rq   r   r   r   r   r   r   r   r  r-  r1  __all__r   r3   r2   <module>rD     s  , - , , , , , , , , ,        ! ! ! ! ! ! . . . . . . . . ) ) ) ) ) ) 7 7 7 7 7 7 / / / / / /         
 P O O O O O O O K K K K K K K K F F F F F F F F & & & & & & I I I I I I I I I I 0 0 0 0 0 0 / / / / / / ( ( ( ( ( () ) ) ) )RY ) ) )$	UU\ 	U# 	U%, 	U 	U 	U 	U& % %I%<% 
% <	%
 U\*% % % '(% % % %46 6 6' ' ' 'TB) B) B) B) B)29 B) B) B)J Y''J J J J J J J ('J(!< !< !< !< !< !< !< !<H+ + + + +0 + + +\        $ K
 K
 K
 K
 K
! K
 K
 K
\ H
 H
 H
 H
 H
' H
 H
 H
V	 	 	 	 	#CEW 	 	 		 	 	 	 	 =?Q 	 	 	  r3   