
    iU                        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 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'm(Z( ddl)m*Z*  G d dejV                        Z, G d dejV                        Z- G d dejV                        Z.d Z/dej`                  de1dej`                  fdZ2	 d3dejV                  dej`                  d ej`                  d!ej`                  d"ej`                  dz  d#e3d$e3d%e!e#   fd&Z4d4d'Z5 ee5       G d( d)ejV                               Z6 G d* d+e      Z7e$ G d, d-e             Z8e$ G d. d/e8             Z9e$ G d0 d1e8e             Z:g d2Z;y)5    )Callable)OptionalN   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernelized_func)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maybe_autocast   )
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     p/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/transformers/models/olmo/modeling_olmo.pyr"   zOlmoLayerNorm.__init__3   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$   r(   
orig_dtypes      r&   forwardzOlmoLayerNorm.forward7   sO    "((
||M,,5==,A4CXCXZ^`djnorr
 	
r'   )
__name__
__module____qualname____doc__intr"   r0   Tensorr3   __classcell__r%   s   @r&   r   r   0   s4    9/C /D /
U\\ 
ell 
r'   r   c                   $     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$   rB   r%   s     r&   r"   zOlmoMLP.__init__?   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r'   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r    )rH   rJ   rF   rG   )r$   xrH   s      r&   r3   zOlmoMLP.forwardI   s6    NN4;;t~~a/@#ADLLQRO#ST	r'   )r4   r5   r6   r"   r3   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_freqNrB   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defaultrP   F)
persistentoriginal_inv_freq)r!   r"   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrB   rope_parametersrR   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r$   rB   devicerope_init_fnrP   r%   s        r&   r"   zOlmoRotaryEmbedding.__init__Q   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr'   r^   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*   )r^   r+   )	rY   getattrr   num_attention_headsr0   arangeint64r/   float)rB   r^   r`   basedimattention_factorrP   s          r&   rZ   z3OlmoRotaryEmbedding.compute_default_rope_parametersa   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r'   c                    | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        ||	fS # 1 sw Y   	fS xY w)
Nr   r   mpscpuF)device_typeenabledrd   rk   )rP   ri   expandshaper/   r^   
isinstancetypestrr   	transposer0   catcosr[   sin)
r$   rM   position_idsinv_freq_expandedposition_ids_expandedrq   freqsembr{   r|   s
             r&   r3   zOlmoRotaryEmbedding.forward   s8    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E!((--[`J`ahhmmfkUC 	5&,,.1F1L1L1NNYYZ[]^_E))UEN3C'')d444C'')d444C		5
 Cx	5
 Cxs   BE''E3r    )NNN)r4   r5   r6   r0   r9   __annotations__r   r"   staticmethodr   r8   tupleri   rZ   no_gradr   r3   r:   r;   s   @r&   rO   rO   N   s    llVz V  $(+/"*T!*(* t* 
~u$	%	* *: U]]_
  
r'   rO   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..Nrn   rd   rs   )ru   r0   rz   )rM   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)ru   rt   reshape)r(   r   batchnum_key_value_headsslenrc   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   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 )Nrd   r   rn   )rk   r+   )ptrainingr   )r   num_key_value_groupsr0   matmulry   ru   rD   
functionalsoftmaxr1   r/   r+   r   r   
contiguous)r   r   r   r   r   r   r   r   
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                 
   | 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   r/   )	qkr{   r|   unsqueeze_dimq_typek_typeq_embedk_embeds	            r&   apply_rotary_pos_embr      s|    $ WWaggFF
--
&C
--
&C3w;q>C/0G3w;q>C/0G::fwzz&111r'   c                   
    e Zd ZdZdedef fdZ	 	 ddej                  de	ej                  ej                  f   dej                  dz  d	e
dz  d
ej                  dz  de	ej                  ej                  dz  f   fdZ xZS )OlmoAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrB   	layer_idxc                 d   t         |           || _        || _        t	        |d|j
                  |j                  z        | _        |j                  |j                  z  | _	        | j                  dz  | _
        |j                  | _        d| _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j                  | j                  z  |j
                  |j                        | _        y )Nrc   g      Tr@   )r!   r"   rB   r   re   r   rf   rc   r   r   r   attention_dropout	is_causalrD   rE   attention_biasq_projk_projv_projo_projr$   rB   r   r%   s      r&   r"   zOlmoAttention.__init__   sM   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r'   Nr(   position_embeddingsr   past_key_valuescache_positionr   c                    |j                   d d }g |d| j                  }| j                  |      }	| j                  |      }
| j	                  |      }| j
                  j                  |	j                  | j
                  j                   | j
                  j                         |
j                  | j
                  j                   | j
                  j                         |j                  | j
                  j                   | j
                  j                         |	j                  |      j                  dd      }	|
j                  |      j                  dd      }
|j                  |      j                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        j                  | j
                  j                  t               } || |	|
||f| j"                  sdn| j$                  | j&                  d|\  }} |j(                  g |d j+                         }| j-                  |      }||fS )Nrn   )minmaxr   rd   )r|   r{   r           )r   r   )ru   rc   r   r   r   rB   clip_qkvclamp_viewry   r   updater   r   get_interface_attn_implementationr   r   r   r   r   r   r   )r$   r(   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r{   r|   cache_kwargsattention_interfacer   r   s                     r&   r3   zOlmoAttention.forward   s8    $))#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'6'='=j,X\XfXfht'u$J(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r'   )NN)r4   r5   r6   r7   r   r8   r"   r0   r9   r   r   
LongTensorr3   r:   r;   s   @r&   r   r      s    G
z 
c 
8 )-262)||2) #5<<#=>2) t+	2)
 2) ((4/2) 
u||U\\D00	12)r'   r   c                   "    e Zd Zdedef fdZ	 	 	 	 	 	 ddej                  dej                  dz  dej                  dz  de	dz  d	e
dz  d
ej                  dz  deej                  ej                  f   dz  dee   dej                  fdZ xZS )OlmoDecoderLayerrB   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                        | _        t        |j                        | _	        y )N)rB   r   )
r!   r"   r   r   	self_attnr=   mlpr   input_layernormpost_attention_layernormr   s      r&   r"   zOlmoDecoderLayer.__init__&  s[    !--&f	J6?,V-?-?@(5f6H6H(I%r'   Nr(   r   r}   r   	use_cacher   r   r   r   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r(   r   r}   r   r   r   r    )r   r   r   r   )r$   r(   r   r}   r   r   r   r   r   residual_s              r&   r3   zOlmoDecoderLayer.forward/  s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r'   )NNNFNN)r4   r5   r6   r   r8   r"   r0   r9   r   r   boolr   r   r   r3   r:   r;   s   @r&   r   r   %  s    Jz Jc J /304(,!&26HL|| t+ &&-	
  $; ((4/ #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)OlmoPreTrainedModelrB   modelTr   r   )r(   
attentionsN)r4   r5   r6   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   Q  sQ    &*#+,#4"5N!"&)#r'   r   c                       e Zd Zdef 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   defd              Z xZS )	OlmoModelrB   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rB   F)r!   r"   pad_token_idpadding_idx
vocab_sizerD   	Embeddingr   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   normrO   
rotary_embgradient_checkpointing	post_initr   s      r&   r"   zOlmoModel.__init__f  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   r   c                 D   |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|E||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   )r^   )rB   input_embedsr   r   r   r}   )r}   )r   r   r}   r   r   r   )last_hidden_stater   )
ValueErrorr   r   rB   get_seq_lengthr0   rg   ru   r^   r   r   r   r   r   r   r   )r$   r   r   r}   r   r   r   r   r   past_seen_tokensr   r(   r   decoder_layers                 r&   r3   zOlmoModel.forwardv  s]    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de]003M<P<PQTdd  )33A6L(;;&))+%
 &"oom,oW![[)H4;;+H+HI 
	M)	*$7) /#-	 	M
	 		-0&++
 	
r'   )NNNNNNN)r4   r5   r6   r   r"   r   r   r0   r   r9   r   FloatTensorr   r   r   r   r3   r:   r;   s   @r&   r   r   d  s    z    .2.204(,2626!%9
##d*9
 t+9
 &&-	9

 9
 ((4/9
 ((4/9
 $;9
 +,9
 
!9
  9
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	j                  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 r?   )
r!   r"   r   r   r   rD   rE   r   r	  r   rK   s     r&   r"   zOlmoForCausalLM.__init__  sU     v&
 ++yy!3!3V5F5FUS 	r'   Nr   r   r}   r   r   labelsr   r   logits_to_keepr   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   r   r}   r   r   r   r   N)r  r  r   )lossr  r   r(   r   r   )r   r  rv   r8   slicer	  loss_functionrB   r   r   r   r(   r   )r$   r   r   r}   r   r   r  r   r   r  r   outputsr(   slice_indicesr  r  s                   r&   r3   zOlmoForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r'   )	NNNNNNNNr   )r4   r5   r6   _tied_weights_keys_tp_plan_pp_planr"   r   r   r0   r   r9   r   r  r   r8   r   r   r   r3   r:   r;   s   @r&   r  r    s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.8
##d*8
 t+8
 &&-	8

 8
 ((4/8
   4'8
 $;8
 ((4/8
 ell*8
 +,8
 
 8
  8
r'   r  )r  r   r   )r   )r   )<collections.abcr   typingr   r0   torch.nnrD   torch.nn.functionalr   r-   activationsr   cache_utilsr   r   
generationr	   integrationsr
   masking_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   configuration_olmor   Moduler   r=   rO   r   r9   r8   r   ri   r   r   r   r   r   r   r  __all__r   r'   r&   <module>r+     s  4 %      ! . ) / / 9 O K F & I I ? *
BII 
bii  =")) =@(	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%424 )*L)BII L) +L)^)1 )X /  $ L
# L
 L
^ H
)? H
 H
V Br'   