
     `i[O                        d dl mZmZmZ d dlZd dlmZ d dlmZ ddl	m
Z
 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# ddl$m%Z% ddl&m'Z' ddl(m)Z)  ed           G d dej*                              Z+dej,        de-dej,        fdZ.	 d6dej*        dej,        dej,        dej,        d eej,                 d!e/d"e/d#e e         fd$Z0d7d%Z1d& Z2 G d' d(ej*                  Z3 G d) d*ej*                  Z4 G d+ d,e          Z5 G d- d.ej*                  Z6e" G d/ d0e                      Z7e" G d1 d2e7                      Z8e" G d3 d4e7e                      Z9g d5Z:dS )8    )CallableOptionalUnionN)TransformersKwargs   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)auto_docstringcan_return_tuple)deprecate_kwarg)check_model_inputs   )Olmo2ConfigRMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )Olmo2RMSNormư>c                     t                                                       t          j        t	          j        |                    | _        || _        dS )z;
        Olmo2RMSNorm is equivalent to T5LayerNorm
        N)super__init__nn	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      |/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/olmo2/modeling_olmo2.pyr"   zOlmo2RMSNorm.__init__    sD     	l5:k#:#:;; #    c                    |j         }|                    t          j                  }|                    d                              dd          }|t          j        || j        z             z  }| j        |z                      |          S )N   T)keepdim)	dtypetor%   float32powmeanrsqrtr(   r'   )r)   hidden_statesinput_dtypevariances       r-   forwardzOlmo2RMSNorm.forward(   s|    #)%((77 $$Q'',,R,>>%Ht?T4T(U(UUm+//<<<r.   c                 H    t          | j        j                   d| j         S )Nz, eps=)tupler'   shaper(   )r)   s    r-   
extra_reprzOlmo2RMSNorm.extra_repr/   s&    )**II$2GIIIr.   )r   )__name__
__module____qualname__r"   r<   r@   __classcell__r,   s   @r-   r   r      sb        $ $ $ $ $ $= = =J J J J J J Jr.   r   r9   n_repreturnc                     | j         \  }}}}|dk    r| S | dddddddddf                             |||||          } |                     |||z  ||          S )z
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r   N)r?   expandreshape)r9   rF   batchnum_key_value_headsslenhead_dims         r-   	repeat_kvrO   3   s    
 2?1D.Ehzz!!!!QQQaaa"23::5BUW\^bdlmmM  (;e(CT8TTTr.           modulequerykeyvalueattention_maskscalingdropoutkwargsc                 R   t          || j                  }t          || j                  }	t          j        ||                    dd                    |z  }
|$|d d d d d d d |j        d         f         }|
|z   }
t          j                            |
dt          j	                  
                    |j                  }
t          j                            |
|| j                  }
t          j        |
|	          }|                    dd                                          }||
fS )Nr0   r   r1   )dimr3   )ptrainingr   )rO   num_key_value_groupsr%   matmul	transposer?   r#   
functionalsoftmaxr5   r4   r3   rW   r]   
contiguous)rQ   rR   rS   rT   rU   rV   rW   rX   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r-   eager_attention_forwardri   ?   s    3 ;<<JUF$?@@L<z';';Aq'A'ABBWLL!$QQQ111.D
0@0D.D%DE#k1=((2U](SSVVW\WbccL=((6?([[L,|\::K''1--88::K$$r.   c                 &   | j         |j         }}|                    |          }|                    |          }| |z  t          |           |z  z   }||z  t          |          |z  z   }	|                    |          |	                    |          fS )a  Applies Rotary Position Embedding to the query and key tensors.

    Args:
        q (`torch.Tensor`): The query tensor.
        k (`torch.Tensor`): The key tensor.
        cos (`torch.Tensor`): The cosine part of the rotary embedding.
        sin (`torch.Tensor`): The sine part of the rotary embedding.
        position_ids (`torch.Tensor`, *optional*):
            Deprecated and unused.
        unsqueeze_dim (`int`, *optional*, defaults to 1):
            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
    Returns:
        `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
    )r3   	unsqueezerotate_halfr4   )
qkcossinposition_idsunsqueeze_dimq_typek_typeq_embedk_embeds
             r-   apply_rotary_pos_embrw   Y   s    ( WagFF
--
&
&C
--
&
&C3w;q>>C/0G3w;q>>C/0G::fwzz&1111r.   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..Nr1   r0   r[   )r?   r%   cat)xx1x2s      r-   rl   rl   u   s]    	
3"!'"+"""	#B	
3q """	#B9rc2YB''''r.   c                   .    e Zd ZdZddedee         f fdZ eddd	          	 	 dd
e	j
        dee	j
        e	j
        f         dee	j
                 dee         dee	j                 dee         dee	j
        ee	j
                 f         fd            Z xZS )Olmo2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperNconfig	layer_idxc                 J   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                  | _        t)          |j        | j        z  |j                  | _        t)          |j        | j        z  |j                  | _        d S )NrN   g      Tbias)r!   r"   r   r   getattrr*   num_attention_headsrN   rL   r^   rV   attention_dropout	is_causalr#   Linearattention_biasq_projk_projv_projo_projr   rms_norm_epsq_normk_normr)   r   r   r,   s      r-   r"   zOlmo2Attention.__init__   s   "
F4F&Jd4dee$*$>&B\$\!}d*!'!9i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i&68JQWQf
 
 
 #6#=#MvObcc"6#=#MvObccr.   past_key_valuepast_key_values4.58new_nameversionr9   position_embeddingsrU   cache_positionrX   rG   c                    |j         d d         }g |d| j        R }|                     |                     |                    }	|                     |                     |                    }
|                     |          }|	                    |                              dd          }	|
                    |                              dd          }
|                    |                              dd          }|\  }}t          |	|
||          \  }	}
|&|||d}|
                    |
|| j        |          \  }
}t          }| j        j        dk    rt          | j        j                 } || |	|
||f| j        sdn| j        | j        d|\  }} |j        g |dR                                  }|                     |          }||fS )Nr1   r   r0   )rp   ro   r   eagerrP   )rW   rV   )r?   rN   r   r   r   r   r   viewr`   rw   updater   ri   r   _attn_implementationr   r]   r   rV   rJ   rc   r   )r)   r9   r   rU   r   r   rX   input_shapehidden_shapequery_statesrd   re   ro   rp   cache_kwargsattention_interfacerh   rf   s                     r-   r<   zOlmo2Attention.forward   s    $)#2#.88b8$-88{{4;;}#=#=>>[[]!;!;<<
{{=11#((66@@AFF__\22<<QBB
#((66@@AFF&S#7jRUWZ#[#[ j&#&snUUL'6'='=j,X\Xfht'u'u$J(?;+w66"9$+:Z"[$7$7	%
  $}HCC$2HL	%
 	%
 	%
 	%
!\ *k);;;;;;FFHHkk+..L((r.   N)NN)rA   rB   rC   __doc__r   r   intr"   r   r%   Tensorr>   r	   
LongTensorr   r   r<   rD   rE   s   @r-   r   r   |   s%       GGd d{ dx} d d d d d d2 _%0A6RRR ,059-) -)|-) #5<#=>-) !.	-)
 "%-) !!12-) +,-) 
u|Xel33	4-) -) -) SR-) -) -) -) -)r.   r   c                   $     e Zd Z fdZd Z xZS )Olmo2MLPc                    t                                                       || _        |j        | _        |j        | _        t          j        | j        | j        d          | _        t          j        | j        | j        d          | _        t          j        | j        | j        d          | _	        t          |j                 | _        d S NFr   )r!   r"   r   r*   intermediate_sizer#   r   	gate_projup_proj	down_projr   
hidden_actact_fnr)   r   r,   s     r-   r"   zOlmo2MLP.__init__   s    !-!'!94#3T5KRWXXXy!143IPUVVV4#94;KRWXXXV./r.   c                     |                      |                     |                     |                    |                     |          z            }|S r   )r   r   r   r   )r)   r{   r   s      r-   r<   zOlmo2MLP.forward   sA    NN4;;t~~a/@/@#A#ADLLQROO#STT	r.   )rA   rB   rC   r"   r<   rD   rE   s   @r-   r   r      sG        0 0 0 0 0      r.   r   c                   4    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 )Olmo2DecoderLayerr   r   c                 4   t                                                       |j        | _        t          ||          | _        t          |          | _        t          |j        |j                  | _	        t          |j        |j                  | _
        d S )N)r   r   r+   )r!   r"   r*   r   	self_attnr   mlpr   r   post_attention_layernormpost_feedforward_layernormr   s      r-   r"   zOlmo2DecoderLayer.__init__   s    !-'vKKKF##(4V5GVM`(a(a(a%*6v7IvOb*c*c*c'''r.   r   r   r   r   NFr9   rU   rq   	use_cacher   r   rX   rG   c                     |}	 | j         d|||||||d|\  }}
|                     |          }|	|z   }|}	|                     |          }|                     |          }|	|z   }|S )N)r9   rU   rq   r   r   r   r    )r   r   r   r   )r)   r9   rU   rq   r   r   r   r   rX   residual_s              r-   r<   zOlmo2DecoderLayer.forward   s     !)4> 	
')%+) 3	
 	
 	
 	
q 55mDD =0 !//77FF =0r.   )NNNFNN)rA   rB   rC   r   r   r"   r   r%   r   r   r   r	   boolr>   r   r   r<   rD   rE   s   @r-   r   r      s5       d{ ds d d d d d d _%0A6RRR 2637+/$)59KO | !. u/0	
 "% D> !!12 &eEL%,,F&GH +, 
   SR    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 )Olmo2RotaryEmbeddinginv_freqNr   c                    t                                                       t          |d          rSt          |j        t
                    r9|j                            d|j                            d                    | _        nd| _        |j        | _	        |j        | _
        || _        t          | j                 | _        |                     | j        |          \  }| _        |                     d|d           | j        | _        d S )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_lenr   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r)   r   devicer   r,   s       r-   r"   zOlmo2RotaryEmbedding.__init__  s    6>** 	'z&:Mt/T/T 	'#044[&BUBYBYZ`BaBabbDNN&DN"("@$*$B!/?+/+<+<T[&+Q+Q($(ZeDDD!%r.   c                    | j         d d d d f                                                             |j        d         dd                              |j                  }|d d d d d f                                         }t          |j        j        t                    r|j        j        dk    r|j        j        nd}t          j
        |d          5  |                                |                                z                      dd          }t          j        ||fd	          }|                                | j        z  }|                                | j        z  }	||	fcd d d            S # 1 swxY w Y   d S )
Nr   r1   r   mpscpuF)device_typeenabledr0   ry   )r   floatrI   r?   r4   r   r   r   strr%   autocastr`   rz   ro   r   rp   )
r)   r{   rq   inv_freq_expandedposition_ids_expandedr   freqsembro   rp   s
             r-   r<   zOlmo2RotaryEmbedding.forward  s    !M$4-8>>@@GGHZ[\H]_acdeehhijiqrr ,QQQaaaZ 8 > > @ @'1!(-'E'Ek!(-[`J`J`ahmmfk^UCCC 	 	&,,..1F1L1L1N1NNYYZ[]^__E)UEN333C''))d44C''))d44C8	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	s   BE//E36E3r   )rA   rB   rC   r%   r   __annotations__r   r"   no_gradr   r<   rD   rE   s   @r-   r   r     s         l/ /{ / / / / / /" U]__
 
  _
 
 
 
 
r.   r   c                   L    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dS )Olmo2PreTrainedModelr   modelTr   r   )r9   
attentionsN)rA   rB   rC   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   (  sl         &*#,-#4"5N!"&*$ r.   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej	                 deej
                 deej	                 dee         deej                 d	eej	                 d
ee         dee         defd                        Z xZS )
Olmo2Modelr   c                    t                                                     j        | _        j        | _        t          j        j        j        | j                  | _        t          j	        fdt          j                  D                       | _        t          j        j                  | _        t!                    | _        d| _        |                                  d S )Nc                 0    g | ]}t          |          S r   )r   ).0r   r   s     r-   
<listcomp>z'Olmo2Model.__init__.<locals>.<listcomp>D  s$    cccivy11cccr.   r   r   F)r!   r"   pad_token_idpadding_idx
vocab_sizer#   	Embeddingr*   embed_tokens
ModuleListrangenum_hidden_layerslayersr   r   normr   
rotary_embgradient_checkpointing	post_initr   s    `r-   r"   zOlmo2Model.__init__=  s       !. +L):F<NPTP`aamcccc5IaCbCbccc
 
 !!39LMMM	.f===&+# 	r.   N	input_idsrU   rq   r   inputs_embedsr   r   rX   rG   c           
      N   |d u |d uz  rt          d          ||                     |          }|r|t          | j                  }|B||                                nd}	t          j        |	|	|j        d         z   |j                  }||	                    d          }t          | j        |||||          }
|}|                     ||          }| j        d | j        j                 D ]} ||f|
||||d|}|                     |          }t          ||          S )	Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )r   )r   input_embedsrU   r   r   rq   )rU   rq   r   r   r   )last_hidden_stater   )
ValueErrorr   r
   r   get_seq_lengthr%   aranger?   r   rk   r   r  r  r  r  r   )r)   r	  rU   rq   r   r
  r   r   rX   past_seen_tokensrg   r9   r   decoder_layers                 r-   r<   zOlmo2Model.forwardM  s    -t";< 	[YZZZ *.*;*;I*F*FM 	?0*$+>>>O!CRC^==???de+0< "2]5H5K"KTaTh, , ,N )33A66L(;&))+%
 
 
 &"oom\JJ![)H4;+H)HI 		 		M)M*) /-$7   MM 		-00&++
 
 
 	
r.   )NNNNNNN)rA   rB   rC   r   r"   r   r   r   r%   r   r   r	   FloatTensorr   r   r   r   r<   rD   rE   s   @r-   r   r   ;  s       {         151537+/5959$(8
 8
E,-8
 !.8
 u/0	8

 "%8
   128
 !!128
 D>8
 +,8
 
!8
 8
 8
 ^ 8
 8
 8
 8
 8
r.   r   c                   f    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 )Olmo2ForCausalLMzlm_head.weightlm_headcolwise_repr9   logitsc                     t                                          |           t          |          | _        |j        | _        t          j        |j        |j        d          | _        | 	                                 d S r   )
r!   r"   r   r   r   r#   r   r*   r  r  r   s     r-   r"   zOlmo2ForCausalLM.__init__  sj       ''
 +y!3V5FUSSS 	r.   Nr   r	  rU   rq   r   r
  labelsr   r   logits_to_keeprX   rG   c
                 R    | j         d|||||||d|
}|j        }t          |	t                    rt	          |	 d          n|	}|                     |dd|ddf                   }d}| | j        d||| j        j        d|
}t          |||j
        |j        |j                  S )a  
        Example:

        ```python
        >>> from transformers import AutoTokenizer, Olmo2ForCausalLM

        >>> model = Olmo2ForCausalLM.from_pretrained("meta-olmo2/Olmo2-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-olmo2/Olmo2-2-7b-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	  rU   rq   r   r
  r   r   N)r  r  r   )lossr  r   r9   r   r   )r   r  r   r   slicer  loss_functionr   r   r   r   r9   r   )r)   r	  rU   rq   r   r
  r  r   r   r  rX   outputsr9   slice_indicesr  r  s                   r-   r<   zOlmo2ForCausalLM.forward  s    @ ,64: 	,
)%+')	,
 	,
 	,
 	,
  18B>SV8W8Wk~ot444]kmAAA}aaa,?@AA%4%pVFt{OeppioppD%#3!/)
 
 
 	
r.   )	NNNNNNNNr   )rA   rB   rC   _tied_weights_keys_tp_plan_pp_planr"   r   r   r   r%   r   r   r	   r  r   r   r   r   r   r   r<   rD   rE   s   @r-   r  r    sa       *+=)H_-z:;H      151537+/59-1$(59348
 8
E,-8
 !.8
 u/0	8

 "%8
   128
 )*8
 D>8
 !!128
 c5</08
 +,8
 
 8
 8
 8
 ^ 8
 8
 8
 8
 8
r.   r  )r  r   r   )rP   )Nr   );typingr   r   r   r%   torch.nnr#   transformers.utils.genericr   activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   utils.deprecationr   utils.genericr   configuration_olmo2r   Moduler   r   r   rO   r   ri   rw   rl   r   r   r   r   r   r   r  __all__r   r.   r-   <module>r8     s   - , , , , , , , , ,        9 9 9 9 9 9 ! ! ! ! ! ! . . . . . . . . ) ) ) ) ) ) 7 7 7 7 7 7 / / / / / / 9 9 9 9 9 9 O O O O O O O O K K K K K K K K F F F F F F F F & & & & & & 5 5 5 5 5 5 5 5 0 0 0 0 0 0 / / / / / / , , , , , , Y''J J J J J29 J J ('J(	UU\ 	U# 	U%, 	U 	U 	U 	U& % %I%<% 
% <	%
 U\*% % % '(% % % %42 2 2 28( ( (J) J) J) J) J)RY J) J) J)Z    ry    ) ) ) ) )2 ) ) )X         29      F     ?   $ K
 K
 K
 K
 K
% K
 K
 K
\ H
 H
 H
 H
 H
+_ H
 H
 H
V E
D
Dr.   