
    ^joS                     `   d dl mZ d dl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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 m!Z! ddl"m#Z# ddl$m%Z%m&Z&m'Z' ddl(m)Z)m*Z* ddl+m,Z, ddl-m.Z.  G d dej^                        Z0 G d dej^                        Z1 G d dej^                        Z2d Z3dejh                  de5dejh                  fdZ6	 d7dej^                  d ejh                  d!ejh                  d"ejh                  d#ejh                  dz  d$e7d%e7d&e#e%   fd'Z8 ed(      d8d)       Z9 ee9       G d* d+ej^                               Z: G d, d-e      Z;e& G d. d/e!             Z<e& G d0 d1e<             Z=e& G d2 d3e<e             Z> G d4 d5ee<      Z?g d6Z@y)9    )Callable)OptionalN   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_func_from_hubuse_kernelized_func)create_causal_mask) GenericForSequenceClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs   )
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     q/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/olmo/modeling_olmo.pyr%   zOlmoLayerNorm.__init__4   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.forward8   sO    "((
||M,,5==,A4CXCXZ^`djnorr
 	
r*   )
__name__
__module____qualname____doc__intr%   r3   Tensorr6   __classcell__r(   s   @r)   r   r   1   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'   rE   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#   )rK   rM   rI   rJ   )r'   xrK   s      r)   r6   zOlmoMLP.forwardJ   s6    NN4;;t~~a/@#ADLLQRO#ST	r*   )r7   r8   r9   r%   r6   r=   r>   s   @r)   r@   r@   ?   s    0r*   r@   c                        e Zd ZU ej                  ed<   ddef fdZe	 	 	 ddedz  de	d   de
dz  ded	ef   fd
       Z ej                         ed               Z xZS )OlmoRotaryEmbeddinginv_freqNrE   c                    t         |           |j                  | _        |j                  | _        || _        | j
                  j                  d   | _        | j                  }| j                  dk7  rt        | j                     } || j
                  |      \  }| _
        | j                  d|d       | j                  d|j                         d       y )N	rope_typedefaultrS   F)
persistentoriginal_inv_freq)r$   r%   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrE   rope_parametersrU   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r'   rE   devicerope_init_fnrS   r(   s        r)   r%   zOlmoRotaryEmbedding.__init__R   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr*   ra   ztorch.deviceseq_lenr!   ztorch.Tensorc                    | j                   d   }t        | dd      xs | j                  | j                  z  }d}d|t	        j
                  d|dt        j                        j                  |t        j                        |z  z  z  }||fS )	a  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        
rope_thetahead_dimNg      ?r      r-   )ra   r.   )	r\   getattrr    num_attention_headsr3   arangeint64r2   float)rE   ra   rc   basedimattention_factorrS   s          r)   r]   z3OlmoRotaryEmbedding.compute_default_rope_parametersb   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r*   c                    | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        ||	fS # 1 sw Y   	fS xY w)
Nr   r   mpscpuF)device_typeenabledrg   rn   )rS   rl   expandshaper2   ra   
isinstancetypestrr   	transposer3   catcosr^   sin)
r'   rP   position_idsinv_freq_expandedposition_ids_expandedrt   freqsembr~   r   s
             r)   r6   zOlmoRotaryEmbedding.forward   s8    !MM$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
 Cx	5
 Cxs   BE''E3r#   )NNN)r7   r8   r9   r3   r<   __annotations__r   r%   staticmethodr   r;   tuplerl   r]   no_gradr   r6   r=   r>   s   @r)   rR   rR   O   s    llVz V  $(+/"*T!*(* t* 
~u$	%	* *: U]]_
  
r*   rR   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..Nrq   rg   rv   )rx   r3   r}   )rP   x1x2s      r)   rotate_halfr      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)rx   rw   reshape)r+   r   batchnum_key_value_headsslenrf   s         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        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
||
|z   }
t
        j                  j                  |
dt        j                        j                  |j                        }
t
        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )Nrg   r   rq   )rn   r.   )ptrainingr   )r   num_key_value_groupsr3   matmulr|   rG   
functionalsoftmaxr4   r2   r.   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r)   eager_attention_forwardr      s     3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!#n4==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r*   rotary_pos_embc                 
   | 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.
        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.   	unsqueezer   r2   )	qkr~   r   unsqueeze_dimq_typek_typeq_embedk_embeds	            r)   apply_rotary_pos_embr      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j                  dz  d	e
dz  d
e	ej                  ej                  dz  f   f
dZ xZS )OlmoAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrE   	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 )Nrf   g      TrC   )r$   r%   rE   r   rh   r    ri   rf   r   r   r   attention_dropout	is_causalrG   rH   attention_biasq_projk_projv_projo_projr'   rE   r   r(   s      r)   r%   zOlmoAttention.__init__   sM   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r*   Nr+   position_embeddingsr   past_key_valuesr!   c                    |j                   d d }g |d| j                  }| j                  |      }| j                  |      }	| j	                  |      }
| j
                  j                  |j                  | j
                  j                   | j
                  j                         |	j                  | j
                  j                   | j
                  j                         |
j                  | j
                  j                   | j
                  j                         |j                  |      j                  dd      }|	j                  |      j                  dd      }	|
j                  |      j                  dd      }
|\  }}t        ||	||      \  }}	| |j                  |	|
| j                        \  }	}
t        j                  | j
                  j                  t               } || ||	|
|f| j"                  sdn| j$                  | j&                  d|\  }} |j(                  g |d j+                         }| j-                  |      }||fS )Nrq   )minmaxr   rg           )r   r   )rx   rf   r   r   r   rE   clip_qkvclamp_viewr|   r   updater   r   get_interface_attn_implementationr   r   r   r   r   r   r   )r'   r+   r   r   r   r   input_shapehidden_shapequery_statesr   r   r~   r   attention_interfacer   r   s                   r)   r6   zOlmoAttention.forward   s)    $))#2.88b8$--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&'6'='=j,X\XfXf'g$J(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r*   r#   )r7   r8   r9   r:   r   r;   r%   r3   r<   r   r   r6   r=   r>   s   @r)   r   r      s    G
z 
c 
8 )-/)||/) #5<<#=>/) t+	/)
 /) 
u||U\\D00	1/)r*   r   c                       e Zd Zdedef fdZ	 	 	 	 	 ddej                  dej                  dz  dej                  dz  de	dz  d	e
dz  d
eej                  ej                  f   dz  dee   dej                  fdZ xZS )OlmoDecoderLayerrE   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                        | _        t        |j                        | _	        y )N)rE   r   )
r$   r%   r    r   	self_attnr@   mlpr   input_layernormpost_attention_layernormr   s      r)   r%   zOlmoDecoderLayer.__init__$  s[    !--&f	J6?,V-?-?@(5f6H6H(I%r*   Nr+   r   r   r   	use_cacher   r   r!   c           
          |}| j                  |      } | j                  d||||||d|\  }}	||z   }|}| j                  |      }| j                  |      }||z   }|S )N)r+   r   r   r   r   r    )r   r   r   r   )
r'   r+   r   r   r   r   r   r   residual_s
             r)   r6   zOlmoDecoderLayer.forward-  s     !,,];)4>> 
')%+ 3
 
q !=0 !55mD/ =0r*   )NNNFN)r7   r8   r9   r   r;   r%   r3   r<   
LongTensorr   boolr   r   r   r6   r=   r>   s   @r)   r   r   #  s    Jz Jc J /304(,!&HL|| t+ &&-	
  $; #5<<#=>E +, 
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)OlmoPreTrainedModelrE   modelTr   r   )r+   
attentionsN)r7   r8   r9   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   r*   r)   r   r   M  sQ    &*#+,#4"5N!"&)#r*   r   c                        e Zd Zdef fdZeee	 	 	 	 	 	 ddej                  dz  dej                  dz  dej                  dz  dedz  dej                  dz  d	edz  d
ee   defd                     Z xZS )	OlmoModelrE   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rE   F)r$   r%   pad_token_idpadding_idx
vocab_sizerG   	Embeddingr    embed_tokens
ModuleListrangenum_hidden_layersr   layersr   normrR   
rotary_embgradient_checkpointing	post_initr   s      r)   r%   zOlmoModel.__init__b  s     !.. ++LL):):F<N<NPTP`P`ammBGH`H`BabYfi0b
 "&"4"45	-V<&+# 	 cs   C5N	input_idsr   r   r   inputs_embedsr   r   r!   c           
      <   |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|V||j	                         nd}t        j                  |j                  d   |j                        |z   }|j                  d      }t        | j                  ||||      }	|}
| j                  |
|      }| j                  d | j                  j                   D ]  } ||
f|	||||d|}
 | j                  |
      }
t        |
|	      S )
Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )ra   )rE   r   r   r   r   )r   )r   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r   rE   get_seq_lengthr3   rj   rx   ra   r   r   r   r   r   r   r   )r'   r   r   r   r   r   r   r   past_seen_tokenscausal_maskr+   r   decoder_layers                r)   r6   zOlmoModel.forwardr  sL    -t";<YZZ *.*;*;I*FM0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L(;;')+%
 &"oom,oW![[)H4;;+H+HI 		M)*$7) /# M		 		-0&++
 	
r*   )NNNNNN)r7   r8   r9   r   r%   r   r   r   r3   r   r<   r   FloatTensorr   r   r   r   r6   r=   r>   s   @r)   r   r   `  s    z     .2.204(,26!%2
##d*2
 t+2
 &&-	2

 2
 ((4/2
 $;2
 +,2
 
!2
    2
r*   r   c                   B    e Zd ZddiZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 dd	e	j                  dz  d
e	j                  dz  de	j                  dz  dedz  de	j                  dz  de	j                  dz  dedz  dee	j                  z  dee   defd              Z xZS )OlmoForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr+   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y rB   )
r$   r%   r   r   r   rG   rH   r    r	  r   rN   s     r)   r%   zOlmoForCausalLM.__init__  sU     v&
 ++yy!3!3V5F5FUS 	r*   Nr   r   r   r   r   labelsr   logits_to_keepr   r!   c	           
      x    | 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   r   r   r   r   r   N)r  r  r   )lossr  r   r+   r   r   )r   r   ry   r;   slicer	  loss_functionrE   r   r   r   r+   r   )r'   r   r   r   r   r   r  r   r  r   outputsr+   slice_indicesr  r  s                  r)   r6   zOlmoForCausalLM.forward  s    > ,64:: ,
)%+',
 ,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r*   )NNNNNNNr   )r7   r8   r9   _tied_weights_keys_tp_plan_pp_planr%   r   r   r3   r   r<   r   r  r   r;   r   r   r   r6   r=   r>   s   @r)   r  r    s   *,GH23H_-z:;H  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
r*   r  c                       e Zd Zy)OlmoForSequenceClassificationN)r7   r8   r9   r   r*   r)   r  r    s    r*   r  )r  r  r   r   )r   )r   )Acollections.abcr   typingr   r3   torch.nnrG   torch.nn.functionalr   r0   activationsr   cache_utilsr   r   
generationr	   integrationsr
   r   masking_utilsr   modeling_layersr   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.output_capturingr   configuration_olmor   Moduler   r@   rR   r   r<   r;   r   rl   r   r   r   r   r   r   r  r  __all__r   r*   r)   <module>r.     s  4 %      ! . ) I / [ O K F & I I G 5 *
BII 
bii  =")) =@(	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 *+2 ,24 )*I)BII I) +I)X'1 'T /  $ F
# F
 F
R F
)? F
 F
R	$DFY 	 cr*   