
    rhM                        d dl mZmZmZ d dlZd dlmZ d dlmc 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 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$m%Z% ddl&m'Z'  G d dejP                        Z) G d dejP                        Z*d Z+dejX                  de-dejX                  fdZ.	 d1dejP                  dejX                  dejX                  dejX                  deejX                     de/d e/d!ee!   fd"Z0d2d#Z1 G d$ d%ejP                        Z2 G d& d'e      Z3 G d( d)ejP                        Z4e" G d* d+e             Z5e" G d, d-e5             Z6e" G d. d/e5e             Z7g d0Z8y)3    )CallableOptionalUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)create_causal_mask)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)check_model_inputs   )
OlmoConfigc                   d     e Zd ZdZdeddf fdZdej                  dej                  fdZ xZ	S )OlmoLayerNormz/LayerNorm but with no learnable weight or bias.hidden_sizereturnNc                 2    t         |           |f| _        y N)super__init__normalized_shape)selfr   	__class__s     y/var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/olmo/modeling_olmo.pyr!   zOlmoLayerNorm.__init__   s    !,    hidden_statesc                     |j                   }t        j                  |j                  t        j
                        | j                  d d d      j                  |      S )N)dtypegh㈵>)eps)r)   F
layer_normtotorchfloat32r"   )r#   r'   
orig_dtypes      r%   forwardzOlmoLayerNorm.forward"   sO    "((
||M,,5==,A4CXCXZ^`djnorr
 	
r&   )
__name__
__module____qualname____doc__intr!   r.   Tensorr1   __classcell__r$   s   @r%   r   r      s4    9/C /D /
U\\ 
ell 
r&   r   c                   $     e Zd Z fdZd Z xZS )OlmoMLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        y NFbias)r    r!   configr   intermediate_sizennLinear	gate_projup_proj	down_projr   
hidden_actact_fnr#   r@   r$   s     r%   r!   zOlmoMLP.__init__*   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r&   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r   )rF   rH   rD   rE   )r#   xrF   s      r%   r1   zOlmoMLP.forward4   s6    NN4;;t~~a/@#ADLLQRO#ST	r&   )r2   r3   r4   r!   r1   r8   r9   s   @r%   r;   r;   )   s    0r&   r;   c                     | 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)shaper.   cat)rK   x1x2s      r%   rotate_halfrU   9   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r&   r'   n_repr   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)rQ   expandreshape)r'   rV   batchnum_key_value_headsslenhead_dims         r%   	repeat_kvr^   @   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 )NrN   r   rM   )rP   r)   )ptrainingr   )r^   num_key_value_groupsr.   matmul	transposerQ   rB   
functionalsoftmaxr/   r-   r)   re   rj   
contiguous)r_   r`   ra   rb   rc   rd   re   rf   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r%   eager_attention_forwardrv   L   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                 
   | j                   |j                   }}|j                  |      }|j                  |      }| |z  t        |       |z  z   }||z  t        |      |z  z   }	|j                  |      |	j                  |      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.
    )r)   	unsqueezerU   r-   )
qkcossinposition_idsunsqueeze_dimq_typek_typeq_embedk_embeds
             r%   apply_rotary_pos_embr   f   s|    ( WWaggFF
--
&C
--
&C3w;q>C/0G3w;q>C/0G::fwzz&111r&   c                   ,    e Zd ZdZdedef fdZ	 	 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j                  e
ej                     e
e	ej                        f   fdZ xZS )OlmoAttentionz=Multi-headed attention from 'Attention Is All You Need' paperr@   	layer_idxc                 d   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
                  |j                        | _        y )Nr]   g      Tr>   )r    r!   r@   r   getattrr   num_attention_headsr]   r[   rk   rd   attention_dropout	is_causalrB   rC   attention_biasq_projk_projv_projo_projr#   r@   r   r$   s      r%   r!   zOlmoAttention.__init__   sM   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r&   r'   position_embeddingsrc   past_key_valuecache_positionr   c                    |j                   d d }g |d| j                  }| j                  |      }	| j                  |      }
| j	                  |      }| j
                  j                  |	j                  | j
                  j                   | j
                  j                         |
j                  | j
                  j                   | j
                  j                         |j                  | j
                  j                   | j
                  j                         |	j                  |      j                  dd      }	|
j                  |      j                  dd      }
|j                  |      j                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j
                  j                  dk7  rt        | j
                  j                     } || |	|
||f| j                   sdn| j"                  | j$                  d|\  }} |j&                  g |d j)                         }| j+                  |      }||fS )	NrM   )minmaxr   rN   )r|   r{   r   eager        )re   rd   )rQ   r]   r   r   r   r@   clip_qkvclamp_viewrm   r   updater   rv   _attn_implementationr   rj   r   rd   rY   rp   r   )r#   r'   r   rc   r   r   rf   input_shapehidden_shapequery_statesrq   rr   r{   r|   cache_kwargsattention_interfaceru   rs   s                     r%   r1   zOlmoAttention.forward   sB    $))#2.88b8$--8{{=1[[/
{{=1;;+T[[%9%9$9t{{?S?ST4;;#7#7"7T[[=Q=QRT[[%9%9$9t{{?S?ST#((6@@AF__\2<<QB
#((6@@AF&S#7jRUWZ#[ j%#&snUL'5'<'<ZW[WeWegs't$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r&   )NN)r2   r3   r4   r5   r   r6   r!   r.   r7   tupler   r   
LongTensorr1   r8   r9   s   @r%   r   r      s    G
z 
c 
8 +/592)||2) #5<<#=>2) !.	2)
 !2) !!1!122) 
u||Xell3XeELL>Q5RR	S2)r&   r   c                   (    e Zd Zdedef fdZ	 	 	 	 	 	 ddej                  deej                     deej                     dee
   dee   d	eej                     d
eeej                  ej                  f      dee   deej                     fdZ xZS )OlmoDecoderLayerr@   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                        | _        t        |j                        | _	        y )N)r@   r   )
r    r!   r   r   	self_attnr;   mlpr   input_layernormpost_attention_layernormr   s      r%   r!   zOlmoDecoderLayer.__init__   s[    !--&f	J6?,V-?-?@(5f6H6H(I%r&   r'   rc   r}   r   	use_cacher   r   rf   r   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r'   rc   r}   r   r   r   r    )r   r   r   r   )r#   r'   rc   r}   r   r   r   r   rf   residual_s              r%   r1   zOlmoDecoderLayer.forward   s     !,,];)4>> 	
')%)) 3	
 	
q !=0 !55mD/ =0r&   )NNNFNN)r2   r3   r4   r   r6   r!   r.   r7   r   r   r   boolr   r   r   r1   r8   r9   s   @r%   r   r      s    Jz Jc J 2637*.$)59KO|| !. u//0	
 ! D> !!1!12 &eELL%,,,F&GH +, 
u||	r&   r   c                   ^     e Zd Zddef fdZ ej                         ed               Z xZ	S )OlmoRotaryEmbeddingr@   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defaultinv_freqF)
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)r#   r@   devicer   r$   s       r%   r!   zOlmoRotaryEmbedding.__init__   s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r&   c                    | 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  }	||	fcd d d        S # 1 sw Y   y xY w)
Nr   rM   r   mpscpuF)device_typeenabledrN   rO   )r   floatrX   rQ   r-   r   r   r   strr.   autocastrm   rR   r{   r   r|   )
r#   rK   r}   inv_freq_expandedposition_ids_expandedr   freqsembr{   r|   s
             r%   r1   zOlmoRotaryEmbedding.forward  s2    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E!((--[`J`ahhmmfk^^UC 	&,,.1F1L1L1NNYYZ[]^_E))UEN3C'')d444C'')d444C8	 	 	s    BE22E;r   )
r2   r3   r4   r   r!   r.   no_gradr   r1   r8   r9   s   @r%   r   r      s3    /z /" U]]_
  
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)OlmoPreTrainedModelr@   modelTr   past_key_values)r'   
attentionsN)r2   r3   r4   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     sQ    &*#+,#4"5N!"&)#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j                     d	ee   d
ee   defd              Z xZS )	OlmoModelr@   c           	         t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                        | _        t!        |      | _        d| _        | j'                          y c c}w )N)r@   F)r    r!   pad_token_idpadding_idx
vocab_sizerB   	Embeddingr   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   normr   
rotary_embgradient_checkpointing	post_initr   s      r%   r!   zOlmoModel.__init__3  s     !.. ++LL):):F<N<NPTP`P`ammBGH`H`BabYfi0b
 "&"4"45	-V<&+# 	 cs   C5	input_idsrc   r}   r   inputs_embedsr   r   rf   r   c           
      *   |d u |d uz  rt        d      || j                  |      }|r|
t               }|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@   input_embedsrc   r   r   r}   )rc   r}   r   r   r   )last_hidden_stater   )
ValueErrorr   r	   get_seq_lengthr.   arangerQ   r   rx   r   r@   r   r   r   r   r   )r#   r   rc   r}   r   r   r   r   rf   past_seen_tokensrt   r'   r   decoder_layers                 r%   r1   zOlmoModel.forwardC  sT    -t";<YZZ *.*;*;I*FM0*nO!CRC^==?de+0<< "2]5H5H5K"KTaThTh,N )33A6L(;;&))+%
 &"oom\J![[)H4;;+H+HI 		M)*).-$7 M		 		-0&++
 	
r&   )NNNNNNN)r2   r3   r4   r   r!   r   r   r   r.   r   r7   r   FloatTensorr   r   r   r   r1   r8   r9   s   @r%   r   r   1  s    z    151537+/5959$(8
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 !!1!128
 D>8
 +,8
 
!8
  8
r&   r   c                   p    e Zd ZdgZddiZddgdgfiZ fdZd Z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 )OlmoForCausalLMzlm_head.weightlm_headcolwise_repr'   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y r=   )
r    r!   r   r   r   rB   rC   r   r  r   rI   s     r%   r!   zOlmoForCausalLM.__init__  sU     v&
 ++yy!3!3V5F5FUS 	r&   c                     || _         y r   r   )r#   decoders     r%   set_decoderzOlmoForCausalLM.set_decoder  s	    
r&   c                     | j                   S r   r  )r#   s    r%   get_decoderzOlmoForCausalLM.get_decoder  s    zzr&   r   rc   r}   r   r   labelsr   r   logits_to_keeprf   r   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, OlmoForCausalLM

        >>> model = OlmoForCausalLM.from_pretrained("meta-olmo/Olmo-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-olmo/Olmo-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   rc   r}   r   r   r   r   N)r  r  r   )lossr  r   r'   r   r   )r   r   r   r6   slicer  loss_functionr@   r   r   r   r'   r   )r#   r   rc   r}   r   r   r  r   r   r  rf   outputsr'   slice_indicesr  r  s                   r%   r1   zOlmoForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r&   )	NNNNNNNNr   )r2   r3   r4   _tied_weights_keys_tp_plan_pp_planr!   r	  r  r   r   r   r.   r   r7   r   r   r   r   r6   r   r   r   r1   r8   r9   s   @r%   r  r    s:   *+=)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
r&   r  )r  r   r   )r   )Nr   )9typingr   r   r   r.   torch.nnrB   torch.nn.functionalrn   r+   activationsr   cache_utilsr   r	   
generationr
   masking_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   configuration_olmor   Moduler   r;   rU   r7   r6   r^   r   rv   r   r   r   r   r   r   r  __all__r   r&   r%   <module>r(     s   - ,     ! . ) / 9 O K F & I I / *
BII 
bii  (	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%428L)BII L)^)1 )X")) B /  $ K
# K
 K
\ N
)? N
 N
b Br&   