
    ha                     8   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 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!m"Z" ddl#m$Z$ ddl%m&Z& ddl'm(Z(  e"jR                  e*      Z+d Z,d5dZ-dej\                  de/dej\                  fdZ0	 d6dejb                  dej\                  dej\                  dej\                  deej\                     de2d e2d!ee   fd"Z3 G d# d$ejb                        Z4 ed%       G d& d'ejb                               Z5 G d( d)ejb                        Z6 G d* d+e      Z7e  G d, d-e             Z8 G d. d/ejb                        Z9e  G d0 d1e8             Z:e  G d2 d3e8e             Z;g d4Z<y)7    )CallableOptionalUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuplelogging)deprecate_kwarg)check_model_inputs   )GraniteConfigc                     | dd| j                   d   dz  f   }| d| j                   d   dz  df   }t        j                  | |fd      S )z*Rotates half the hidden dims of the input..N   dim)shapetorchcat)xx1x2s      j/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/granite/modeling_granite.pyrotate_halfr*   .   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''    c                     |j                  |      }|j                  |      }| |z  t        |       |z  z   }||z  t        |      |z  z   }||fS )a  Applies Rotary Position Embedding to the query and key tensors.

    Args:
        q (`torch.Tensor`): The query tensor.
        k (`torch.Tensor`): The key tensor.
        cos (`torch.Tensor`): The cosine part of the rotary embedding.
        sin (`torch.Tensor`): The sine part of the rotary embedding.
        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.
    )	unsqueezer*   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r)   apply_rotary_pos_embr6   5   sY    ( --
&C
--
&C3w;q>C/0G3w;q>C/0GGr+   hidden_statesn_repreturnc                     | 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)r#   expandreshape)r7   r8   batchnum_key_value_headsslenhead_dims         r)   	repeat_kvrA   P   so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr+   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   r   )r"   dtype)ptrainingr   )rA   num_key_value_groupsr$   matmul	transposer#   r   
functionalsoftmaxfloat32torL   rH   rN   
contiguous)rB   rC   rD   rE   rF   rG   rH   rI   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r)   eager_attention_forwardr\   \   s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#k1==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r+   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 )GraniteAttentionz=Multi-headed attention from 'Attention Is All You Need' paperconfig	layer_idxc                 ^   t         |           || _        || _        t	        |d|j
                  |j                  z        | _        |j                  |j                  z  | _	        |j                  | _        |j                  | _        d| _        t        j                  |j
                  |j                  | j                  z  |j                         | _        t        j                  |j
                  |j                  | j                  z  |j                         | _        t        j                  |j
                  |j                  | j                  z  |j                         | _        t        j                  |j                  | j                  z  |j
                  |j                         | _        y )Nr@   Tbias)super__init__r_   r`   getattrhidden_sizenum_attention_headsr@   r>   rO   attention_multiplierrG   attention_dropout	is_causalr   Linearattention_biasq_projk_projv_projo_projselfr_   r`   	__class__s      r)   re   zGraniteAttention.__init__y   sJ   "
F4F4F&JdJd4de$*$>$>&B\B\$\!22!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r+   past_key_valuepast_key_values4.58new_nameversionr7   position_embeddingsrF   cache_positionrI   r9   c                 4   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                  sdn| j                  | j                   d|\  }} |j"                  g |d j%                         }| j'                  |      }||fS )Nr   r   r    )r1   r0   r|   eager        )rH   rG   )r#   r@   rn   viewrQ   ro   rp   r6   updater`   r\   r_   _attn_implementationr   rN   rj   rG   r<   rV   rq   )rs   r7   r{   rF   rv   r|   rI   input_shapehidden_shapequery_statesrW   rX   r0   r1   cache_kwargsattention_interfacer[   rY   s                     r)   forwardzGraniteAttention.forward   s    $))#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$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r+   N)NN)__name__
__module____qualname____doc__r   r   intre   r   r$   Tensortupler	   
LongTensorr   r   r   __classcell__rt   s   @r)   r^   r^   v   s    G
} 
# 
. %0A6R ,059))||)) #5<<#=>)) !.	))
 "%)) !!1!12)) +,)) 
u||U\\)	*)) S))r+   r^   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )GraniteRMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z=
        GraniteRMSNorm is equivalent to T5LayerNorm
        N)rd   re   r   	Parameterr$   onesweightvariance_epsilon)rs   rg   epsrt   s      r)   re   zGraniteRMSNorm.__init__   s1     	ll5::k#:; #r+   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )Nr    r   T)keepdim)	rL   rU   r$   rT   powmeanrsqrtr   r   )rs   r7   input_dtypevariances       r)   r   zGraniteRMSNorm.forward   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r+   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)r   r   r#   r   )rs   s    r)   
extra_reprzGraniteRMSNorm.extra_repr   s*    ))*+6$2G2G1HIIr+   )gư>)r   r   r   re   r   r   r   r   s   @r)   r   r      s    $;Jr+   r   c                   $     e Zd Z fdZd Z xZS )
GraniteMLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  |j                        | _        t        j                  | j                  | j                  |j                        | _	        t        j                  | j                  | j                  |j                        | _
        t        |j                     | _        y )Nrb   )rd   re   r_   rg   intermediate_sizer   rl   mlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnrs   r_   rt   s     r)   re   zGraniteMLP.__init__   s    !--!'!9!94#3#3T5K5KRXRaRabyy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../r+   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r   )r   r   r   r   )rs   r&   r   s      r)   r   zGraniteMLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r+   )r   r   r   re   r   r   r   s   @r)   r   r      s    0r+   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   de	ej                     de	eej                  ej                  f      deej                  e	eej                  ej                  f      f   fd       Z xZS )GraniteDecoderLayerr_   r`   c                 B   t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        |j                  | _        y )N)r_   r`   r   )rd   re   rg   r^   	self_attnr   mlpr   rms_norm_epsinput_layernormpost_attention_layernormresidual_multiplierrr   s      r)   re   zGraniteDecoderLayer.__init__   sz    !--)9Mf%-f.@.@fFYFYZ(6v7I7IvObOb(c%#)#=#= r+   ru   rv   rw   rx   r7   rF   r2   output_attentions	use_cacher|   r{   r9   c	                    |}
| j                  |      } | j                  d||||||||d|	\  }}|
|| j                  z  z   }|}
| j                  |      }| j	                  |      }|
|| j                  z  z   }|f}|r||fz  }|S )a/  
        Args:
            hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
            attention_mask (`torch.FloatTensor`, *optional*):
                attention mask of size `(batch_size, sequence_length)` if flash attention is used or `(batch_size, 1,
                query_sequence_length, key_sequence_length)` if default attention is used.
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
            use_cache (`bool`, *optional*):
                If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
                (see `past_key_values`).
            past_key_values (`Tuple(torch.FloatTensor)`, *optional*): cached past key and value projection states
            cache_position (`torch.LongTensor` of shape `(sequence_length)`, *optional*):
                Indices depicting the position of the input sequence tokens in the sequence
            position_embeddings (`tuple[torch.FloatTensor, torch.FloatTensor]`, *optional*):
                Tuple containing the cosine and sine positional embeddings of shape `(batch_size, seq_len, head_dim)`,
                with `head_dim` being the embedding dimension of each attention head.
            kwargs (`dict`, *optional*):
                Arbitrary kwargs to be ignored, used for FSDP and other methods that injects code
                into the model
        )r7   rF   r2   rv   r   r   r|   r{    )r   r   r   r   r   )rs   r7   rF   r2   rv   r   r   r|   r{   rI   residualself_attn_weightsoutputss                r)   r   zGraniteDecoderLayer.forward   s    F !,,]; ,:4>> 
,
')%+/) 3
,
 
,
(( !=43K3K#KK !55mD/ =43K3K#KK ")++Gr+   )NNNFFNN)r   r   r   r   r   re   r   r$   r   r   r   r	   boolr   FloatTensorr   r   r   s   @r)   r   r      s   >} > > %0A6R 2637+/,1$)59KO?||? !.? u//0	?
 "%? $D>? D>? !!1!12? &eELL%,,,F&GH? 
u  (51B1BEDUDU1U+V"WW	X? S?r+   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)GranitePreTrainedModelr_   modelTr   rv   )r7   
attentionsN)r   r   r   r   __annotations__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   r+   r)   r   r   0  sQ    &*#./#4"5N!"&,&r+   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 )GraniteRotaryEmbedding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)rd   re   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)rs   r_   devicer   rt   s       r)   re   zGraniteRotaryEmbedding.__init__F  s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r+   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   r   r   mpscpuF)device_typeenabledr    r!   )rL   )r   floatr;   r#   rU   r   r   r   strr$   autocastrQ   r%   r0   r   r1   rL   )
rs   r&   r2   inv_freq_expandedposition_ids_expandedr   freqsembr0   r1   s
             r)   r   zGraniteRotaryEmbedding.forwardW  sV    !MM$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$cff177f&;;;	5 	5s    BF%%F.r   )r   r   r   r$   r   r   r   re   no_gradr   r   r   r   s   @r)   r   r   C  s=    ll/} /" U]]_<  <r+   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   d	ee   d
ee   deej                     dee   defd              Z xZS )GraniteModelr_   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(                  | _        | j+                          y c c}w )Nr   r_   F)rd   re   pad_token_idpadding_idx
vocab_sizer   	Embeddingrg   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normr   
rotary_embgradient_checkpointingembedding_multiplier	post_initrr   s      r)   re   zGraniteModel.__init__i  s     !.. ++LL):):F<N<NPTP`P`ammEJ6KcKcEde	 3e
 #6#5#56;N;NO	0?&+#$*$?$?! 	 fs   D	input_idsrF   r2   rv   inputs_embedsr   r   output_hidden_statesr|   rI   r9   c
                    ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }|d u |d uz  rt	        d      | j
                  r%| j                  r|rt        j                  d       d}|| j                  |      }|| j                  z  }|r|t        | j                         }|	F||j                         nd}t        j                  |||j                  d   z   |j                         }	||	j#                  d      }t%        | j                   |||	||      }|}| j'                  ||      }|rd	nd }|rd	nd }| j(                  d | j                   j*                   D ],  }|r||fz  } ||f||||||	|d
|
}|d   }|s$||d   fz  }. | j-                  |      }|r||fz  }t/        ||r|nd ||      S )Nz:You must specify exactly one of input_ids or inputs_embedszX`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.Fr   r   r   )r   )r_   input_embedsrF   r|   rv   r2   r   )rF   r2   rv   r   r   r|   r{   )last_hidden_staterv   r7   r   )r_   r   r
  r   
ValueErrorr  rN   loggerwarning_oncer   r  r
   get_seq_lengthr$   aranger#   r   r-   r   r  r  r  r  r   )rs   r  rF   r2   rv   r	  r   r   r
  r|   rI   past_seen_tokensrZ   r7   r{   all_hidden_statesall_self_attnsdecoder_layerlayer_outputss                      r)   r   zGraniteModel.forwardz  sN    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I  --i8M%(A(AA0*$++>O!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L(;;&))+%
 & #oom\J #7BD0d![[)H4;;+H+HI 	6M#!m%55!)
*) /"3#-$7
 
M *!,M =#3"55'	6* 		-0  -!11&+/8Od+%	
 	
r+   )	NNNNNNNNN)r   r   r   r   re   r   r   r   r$   r   r   r	   r   r   r   r   r   r   r   r   s   @r)   r   r   g  s   } "  151537+/59$(,0/359_
E,,-_
 !._
 u//0	_

 "%_
   1 12_
 D>_
 $D>_
 'tn_
 !!1!12_
 +,_
 
!_
  _
r+   r   c                       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eee
j                      f      de	e
j                      de	e
j                     de	e   de	e   de	e   de	e
j                     deee
j                  f   dee   defd              Z xZS )GraniteForCausalLMzlm_head.weightlm_headcolwise_repr7   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFrb   )
rd   re   r   r   r   r   rl   rg   r  r  r   s     r)   re   zGraniteForCausalLM.__init__  sU     !&)
 ++yy!3!3V5F5FUS 	r+   r  rF   r2   rv   r	  labelsr   r   r
  r|   logits_to_keeprI   r9   c                    ||n| j                   j                  }|	|	n| j                   j                  }	 | j                  d||||||||	|
d	|}|j                  }t        |t              rt        | d      n|}| j                  |dd|ddf         }|| j                   j                  z  }d}|* | j                  d||| j                   j                  d|}t        |||j                  |j                  |j                        S )a  
        Example:

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

        >>> model = GraniteForCausalLM.from_pretrained("meta-granite/Granite-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-granite/Granite-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."
        ```N)	r  rF   r2   rv   r	  r   r   r
  r|   )r  r  r   )lossr  rv   r7   r   r   )r_   r   r
  r   r  r   r   slicer  logits_scalingloss_functionr   r   rv   r7   r   )rs   r  rF   r2   rv   r	  r  r   r   r
  r|   r  rI   r   r7   slice_indicesr  r!  s                     r)   r   zGraniteForCausalLM.forward  s/   D 2C1N-TXT_T_TqTq$8$D $++JjJj 	
 ,64:: ,
)%+'/!5),
 ,
  118B>SV8W~ot4]kmA}a,?@A$++444%4%%pVFt{{OeOepiopD%#33!//))
 	
r+   )NNNNNNNNNNr   )r   r   r   _tied_weights_keys_tp_plan_pp_planre   r   r   r   r$   r   r   r   r	   listr   r   r   r   r   r   r   r   r   s   @r)   r  r    sw   *+=)H_-z:;H  151537KO59-1$(,0/35934C
E,,-C
 !.C
 u//0	C

 "%tE4E4E/F(F"GHC
   1 12C
 ))*C
 D>C
 $D>C
 'tnC
 !!1!12C
 c5<</0C
 +,C
 
 C
  C
r+   r  )r  r   r   )Nr   )r   )=typingr   r   r   r$   r   activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   utils.deprecationr   utils.genericr   configuration_graniter   
get_loggerr   r  r*   r6   r   r   rA   Moduler   r\   r^   r   r   r   r   r   r   r  __all__r   r+   r)   <module>r<     s  , - ,   ! . ) 7 / 9 O K F & R R 0 / 0 
		H	%(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4D)ryy D)N Y'JRYY J (J(  K4 K\ _  $!<RYY !<H s
) s
 s
l S
/ S
 S
l Kr+   