
    hM                         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$m%Z% ddl&m'Z' ddl(m)Z)  G d dejT                        Z+ G d dejT                        Z,d Z-dej\                  de/dej\                  fdZ0	 d2dejT                  dej\                  dej\                  dej\                  deej\                     d e1d!e1d"ee!   fd#Z2d3d$Z3 G d% d&ejT                        Z4 G d' d(e      Z5 G d) d*ejT                        Z6e" G d+ d,e             Z7e" G d- d.e7             Z8e" G d/ d0e7e             Z9g d1Z:y)4    )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)deprecate_kwarg)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     d/var/www/html/eduruby.in/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$   r(   
orig_dtypes      r&   forwardzOlmoLayerNorm.forward#   sO    "((
||M,,5==,A4CXCXZ^`djnorr
 	
r'   )
__name__
__module____qualname____doc__intr"   r/   Tensorr2   __classcell__r%   s   @r&   r   r      s4    9/C /D /
U\\ 
ell 
r'   r   c                   $     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$   rA   r%   s     r&   r"   zOlmoMLP.__init__+   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r'   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r    )rG   rI   rE   rF   )r$   xrG   s      r&   r2   zOlmoMLP.forward5   s6    NN4;;t~~a/@#ADLLQRO#ST	r'   )r3   r4   r5   r"   r2   r9   r:   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)rL   x1x2s      r&   rotate_halfrV   :   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)rR   expandreshape)r(   rW   batchnum_key_value_headsslenhead_dims         r&   	repeat_kvr_   A   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 )NrO   r   rN   )rQ   r*   )ptrainingr   )r_   num_key_value_groupsr/   matmul	transposerR   rC   
functionalsoftmaxr0   r.   r*   rf   rk   
contiguous)r`   ra   rb   rc   rd   re   rf   rg   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r&   eager_attention_forwardrw   M   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*   	unsqueezerV   r.   )
qkcossinposition_idsunsqueeze_dimq_typek_typeq_embedk_embeds
             r&   apply_rotary_pos_embr   g   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 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j                  eej                     f   fd       Z xZS )OlmoAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrA   	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"   rA   r   getattrr   num_attention_headsr^   r\   rl   re   attention_dropout	is_causalrC   rD   attention_biasq_projk_projv_projo_projr$   rA   r   r%   s      r&   r"   zOlmoAttention.__init__   sM   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r'   past_key_valuepast_key_values4.58new_nameversionr(   position_embeddingsrd   cache_positionr   c                    |j                   d d }g |d| j                  }| j                  |      }	| j                  |      }
| j	                  |      }| j
                  j                  |	j                  | j
                  j                   | j
                  j                         |
j                  | j
                  j                   | j
                  j                         |j                  | j
                  j                   | j
                  j                         |	j                  |      j                  dd      }	|
j                  |      j                  dd      }
|j                  |      j                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j
                  j                  dk7  rt        | j
                  j                     } || |	|
||f| j                   sdn| j"                  | j$                  d|\  }} |j&                  g |d j)                         }| j+                  |      }||fS )	NrN   )minmaxr   rO   )r}   r|   r   eager        )rf   re   )rR   r^   r   r   r   rA   clip_qkvclamp_viewrn   r   updater   rw   _attn_implementationr   rk   r   re   rZ   rq   r   )r$   r(   r   rd   r   r   rg   input_shapehidden_shapequery_statesrr   rs   r|   r}   cache_kwargsattention_interfacerv   rt   s                     r&   r2   zOlmoAttention.forward   sB    $))#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'6'='=j,X\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r'   )NN)r3   r4   r5   r6   r   r7   r"   r   r/   r8   tupler   r   
LongTensorr2   r9   r:   s   @r&   r   r      s    G
z 
c 
. %0A6R ,0592)||2) #5<<#=>2) !.	2)
 "%2) !!1!122) 
u||Xell33	42) S2)r'   r   c                   >    e Zd Zdedef fdZ eddd      	 	 	 	 	 	 ddej                  d	e	ej                     d
e	ej                     de	e   de	e   de	ej                     de	eej                  ej                  f      dee   dej                  fd       Z xZS )OlmoDecoderLayerrA   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                        | _        t        |j                        | _	        y )N)rA   r   )
r!   r"   r   r   	self_attnr<   mlpr   input_layernormpost_attention_layernormr   s      r&   r"   zOlmoDecoderLayer.__init__   s[    !--&f	J6?,V-?-?@(5f6H6H(I%r'   r   r   r   r   r(   rd   r~   	use_cacher   r   rg   r   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r(   rd   r~   r   r   r   r    )r   r   r   r   )r$   r(   rd   r~   r   r   r   r   rg   residual_s              r&   r2   zOlmoDecoderLayer.forward   s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r'   )NNNFNN)r3   r4   r5   r   r7   r"   r   r/   r8   r   r   r   boolr   r   r   r2   r9   r:   s   @r&   r   r      s    Jz Jc J %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 Sr'   r   c                   ~     e Zd ZU ej                  ed<   ddef fdZ ej                         e	d               Z
 xZS )OlmoRotaryEmbeddinginv_freqrA   c                    t         |           t        |d      rUt        |j                  t
              r;|j                  j                  d|j                  j                  d            | _        nd| _        |j                  | _	        |j                  | _
        || _        t        | j                     | _        | j                  | j                  |      \  }| _        | j                  d|d       | j                   | _        y )Nrope_scaling	rope_typetypedefaultr   F)
persistent)r!   r"   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrA   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r$   rA   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   rN   r   mpscpuF)device_typeenabledrO   rP   )r   floatrY   rR   r.   r   r   r   strr/   autocastrn   rS   r|   r   r}   )
r$   rL   r~   inv_freq_expandedposition_ids_expandedr   freqsembr|   r}   s
             r&   r2   zOlmoRotaryEmbedding.forward  s2    !MM$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    )r3   r4   r5   r/   r8   __annotations__r   r"   no_gradr   r2   r9   r:   s   @r&   r   r      s=    ll/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)OlmoPreTrainedModelrA   modelTr   r   )r(   
attentionsN)r3   r4   r5   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   #  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 )	OlmoModelrA   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rA   F)r!   r"   pad_token_idpadding_idx
vocab_sizerC   	Embeddingr   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   normr   
rotary_embgradient_checkpointing	post_initr   s      r&   r"   zOlmoModel.__init__8  s     !.. ++LL):):F<N<NPTP`P`ammBGH`H`BabYfi0b
 "&"4"45	-V<&+# 	 cs   C5	input_idsrd   r~   r   inputs_embedsr   r   rg   r   c           
      B   |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|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   )rA   input_embedsrd   r   r   r~   )rd   r~   r   r   r   )last_hidden_stater   )
ValueErrorr   r	   rA   get_seq_lengthr/   arangerR   r   ry   r   r   r   r   r   r   )r$   r   rd   r~   r   r   r   r   rg   past_seen_tokensru   r(   r   decoder_layers                 r&   r2   zOlmoModel.forwardH  s[    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de+0<< "2]5H5H5K"KTaThTh,N )33A6L(;;&))+%
 &"oom\J![[)H4;;+H+HI 		M)*) /-$7 M		 		-0&++
 	
r'   )NNNNNNN)r3   r4   r5   r   r"   r   r   r   r/   r   r8   r   FloatTensorr   r   r   r   r2   r9   r:   s   @r&   r   r   6  s    z    151537+/5959$(8
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 !!1!128
 D>8
 +,8
 
!8
  8
r'   r   c                   d    e Zd ZdgZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dde	e
j                     de	e
j                     d	e	e
j                     d
e	e   de	e
j                     de	e
j                     de	e   de	e
j                     deee
j                  f   dee   defd              Z xZS )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   rC   rD   r   r  r   rJ   s     r&   r"   zOlmoForCausalLM.__init__  sU     v&
 ++yy!3!3V5F5FUS 	r'   r   rd   r~   r   r   labelsr   r   logits_to_keeprg   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   rd   r~   r   r   r   r   N)r
  r  r   )lossr
  r   r(   r   r   )r   r   r   r7   slicer  loss_functionrA   r   r   r   r(   r   )r$   r   rd   r~   r   r   r  r   r   r  rg   outputsr(   slice_indicesr
  r  s                   r&   r2   zOlmoForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r'   )	NNNNNNNNr   )r3   r4   r5   _tied_weights_keys_tp_plan_pp_planr"   r   r   r   r/   r   r8   r   r  r   r   r7   r   r   r   r2   r9   r:   s   @r&   r  r    s0   *+=)H_-z:;H  151537+/59-1$(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   );typingr   r   r   r/   torch.nnrC   torch.nn.functionalro   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.deprecationr   utils.genericr   configuration_olmor   Moduler   r<   rV   r8   r7   r_   r   rw   r   r   r   r   r   r   r  __all__r   r'   r&   <module>r)     s   - ,     ! . ) / 9 O K F & I I 0 / *
BII 
bii  (	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%428M)BII M)`*1 *Z "))  F /  $ K
# K
 K
\ H
)? H
 H
V Br'   