
     `iM                        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$m%Z% ddl&m'Z' ddl(m)Z)  G d dej*                  Z+ G d dej*                  Z,d Z-dej.        de/dej.        fdZ0	 d3dej*        dej.        dej.        dej.        d eej.                 d!e1d"e1d#ee!         fd$Z2d4d%Z3 G d& d'ej*                  Z4 G d( d)e          Z5 G d* d+ej*                  Z6e" G d, d-e                      Z7e" G d. d/e7                      Z8e" G d0 d1e7e                      Z9g d2Z:dS )5    )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                   P     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                 X    t                                                       |f| _        d S N)super__init__normalized_shape)selfr   	__class__s     z/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/olmo/modeling_olmo.pyr"   zOlmoLayerNorm.__init__   s)    !,    hidden_statesc                     |j         }t          j        |                    t          j                  | j        d d d                              |          S )N)dtypegh㈵>)eps)r*   F
layer_normtotorchfloat32r#   )r$   r(   
orig_dtypes      r&   forwardzOlmoLayerNorm.forward#   sS    "(
|M,,5=,AA4CXZ^`djnooorr
 
 	
r'   )
__name__
__module____qualname____doc__intr"   r/   Tensorr2   __classcell__r%   s   @r&   r   r      sw        99/C /D / / / / / /
U\ 
el 
 
 
 
 
 
 
 
r'   r   c                   $     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                 | _        d S NFbias)r!   r"   configr   intermediate_sizennLinear	gate_projup_proj	down_projr   
hidden_actact_fnr$   rA   r%   s     r&   r"   zOlmoMLP.__init__+   s    !-!'!94#3T5KRWXXXy!143IPUVVV4#94;KRWXXXV./r'   c                     |                      |                     |                     |                    |                     |          z            }|S r    )rG   rI   rE   rF   )r$   xrG   s      r&   r2   zOlmoMLP.forward5   sA    NN4;;t~~a/@/@#A#ADLLQROO#STT	r'   )r3   r4   r5   r"   r2   r9   r:   s   @r&   r<   r<   *   sG        0 0 0 0 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   :   s]    	
3"!'"+"""	#B	
3q """	#B9rc2YB''''r'   r(   n_repr   c                     | 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)rR   expandreshape)r(   rW   batchnum_key_value_headsslenhead_dims         r&   	repeat_kvr_   A   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  }
|$|d d d d d d d |j        d         f         }|
|z   }
t          j                            |
dt          j	                  
                    |j                  }
t          j                            |
|| j                  }
t          j        |
|	          }|                    dd                                          }||
fS )NrO   r   rN   )rQ   r*   )ptrainingr   )r_   num_key_value_groupsr/   matmul	transposerR   rC   
functionalsoftmaxr0   r.   r*   rg   rl   
contiguous)ra   rb   rc   rd   re   rf   rg   rh   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r&   eager_attention_forwardrx   M   s    3 ;<<JUF$?@@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.
    )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    ( WagFF
--
&
&C
--
&
&C3w;q>>C/0G3w;q>>C/0G::fwzz&1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                    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                  | _        d S )Nr^   g      Tr?   )r!   r"   rA   r   getattrr   num_attention_headsr^   r\   rm   rf   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__   sB   "
F4F&Jd4dee$*$>&B\$\!}d*!'!9i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i :T] JQWQf
 
 
 i&68JQWQf
 
 
r'   past_key_valuepast_key_values4.58new_nameversionNr(   position_embeddingsre   cache_positionr   c                 p   |j         d d         }g |d| j        R }|                     |          }	|                     |          }
|                     |          }| j        j        |	                    | j        j         | j        j                   |
                    | j        j         | j        j                   |                    | j        j         | j        j                   |	                    |          	                    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 )	NrN   )minmaxr   rO   )r~   r}   r   eagerr`   )rg   rf   )rR   r^   r   r   r   rA   clip_qkvclamp_viewro   r   updater   rx   _attn_implementationr   rl   r   rf   rZ   rr   r   )r$   r(   r   re   r   r   rh   input_shapehidden_shapequery_statesrs   rt   r}   r~   cache_kwargsattention_interfacerw   ru   s                     r&   r2   zOlmoAttention.forward   s_    $)#2#.88b8$-88{{=11[[//
{{=11;+T[%9$9t{?STTT4;#7"7T[=QRRRT[%9$9t{?STTT#((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$2HL	%
 	%
 	%
 	%
!\ *k);;;;;;FFHHkk+..L((r'   )NN)r3   r4   r5   r6   r   r7   r"   r   r/   r8   tupler   r   
LongTensorr2   r9   r:   s   @r&   r   r      s       GG
z 
c 
 
 
 
 
 
. _%0A6RRR ,0592) 2)|2) #5<#=>2) !.	2)
 "%2) !!122) 
u|Xel33	42) 2) 2) SR2) 2) 2) 2) 2)r'   r   c                   4    e Zd Zdedef fdZ eddd          	 	 	 	 	 	 dd
ej        de	ej                 de	ej
                 de	e         de	e         de	ej
                 de	eej        ej        f                  dee         dej        fd            Z xZS )OlmoDecoderLayerrA   r   c                    t                                                       |j        | _        t          ||          | _        t          |          | _        t          |j                  | _        t          |j                  | _	        d S )N)rA   r   )
r!   r"   r   r   	self_attnr<   mlpr   input_layernormpost_attention_layernormr   s      r&   r"   zOlmoDecoderLayer.__init__   sq    !-&f	JJJ6??,V-?@@(5f6H(I(I%%%r'   r   r   r   r   NFr(   re   r   	use_cacher   r   rh   r   c                     |}	|                      |          } | j        d|||||||d|\  }}
|	|z   }|}	|                     |          }|                     |          }|	|z   }|S )N)r(   re   r   r   r   r   r    )r   r   r   r   )r$   r(   re   r   r   r   r   r   rh   residual_s              r&   r2   zOlmoDecoderLayer.forward   s     !,,];;)4> 	
')%+) 3	
 	
 	
 	
q !=0 !55mD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      s5       Jz Jc J J J J J J _%0A6RRR 2637+/$)59KO | !. u/0	
 "% D> !!12 &eEL%,,F&GH +, 
   SR    r'   r   c                   |     e Zd ZU ej        ed<   ddef fdZ ej                    e	d                         Z
 xZS )OlmoRotaryEmbeddinginv_freqNrA   c                    t                                                       t          |d          rSt          |j        t
                    r9|j                            d|j                            d                    | _        nd| _        |j        | _	        |j        | _
        || _        t          | j                 | _        |                     | j        |          \  }| _        |                     d|d           | j        | _        d S )Nrope_scaling	rope_typetypedefaultr   F)
persistent)r!   r"   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrA   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r$   rA   devicer   r%   s       r&   r"   zOlmoRotaryEmbedding.__init__  s    6>** 	'z&:Mt/T/T 	'#044[&BUBYBYZ`BaBabbDNN&DN"("@$*$B!/?+/+<+<T[&+Q+Q($(ZeDDD!%r'   c                    | j         d d d d f                                                             |j        d         dd                              |j                  }|d d d d d f                                         }t          |j        j        t                    r|j        j        dk    r|j        j        nd}t          j
        |d          5  |                                |                                z                      dd          }t          j        ||fd	          }|                                | j        z  }|                                | j        z  }	||	fcd d d            S # 1 swxY w Y   d S )
Nr   rN   r   mpscpuF)device_typeenabledrO   rP   )r   floatrY   rR   r.   r   r   r   strr/   autocastro   rS   r}   r   r~   )
r$   rL   r   inv_freq_expandedposition_ids_expandedr   freqsembr}   r~   s
             r&   r2   zOlmoRotaryEmbedding.forward  s    !M$4-8>>@@GGHZ[\H]_acdeehhijiqrr ,QQQaaaZ 8 > > @ @'1!(-'E'Ek!(-[`J`J`ahmmfk^UCCC 	 	&,,..1F1L1L1N1NNYYZ[]^__E)UEN333C''))d44C''))d44C8	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	s   BE//E36E3r    )r3   r4   r5   r/   r8   __annotations__r   r"   no_gradr   r2   r9   r:   s   @r&   r   r      s         l/ /z / / / / / /" U]__
 
  _
 
 
 
 
r'   r   c                   L    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZdS )OlmoPreTrainedModelrA   modelTr   r   )r(   
attentionsN)r3   r4   r5   r   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr   r'   r&   r   r   #  sl         &*#+,#4"5N!"&)# r'   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej	                 deej
                 deej	                 dee         deej                 d	eej	                 d
ee         dee         defd                        Z xZS )	OlmoModelrA   c                    t                                                     j        | _        j        | _        t          j        j        j        | j                  | _        t          j	        fdt          j                  D                       | _        t          j                  | _        t                    | _        d| _        |                                  d S )Nc                 0    g | ]}t          |          S r   )r   ).0r   rA   s     r&   
<listcomp>z&OlmoModel.__init__.<locals>.<listcomp>?  s$    bbbYfi00bbbr'   rA   F)r!   r"   pad_token_idpadding_idx
vocab_sizerC   	Embeddingr   embed_tokens
ModuleListrangenum_hidden_layerslayersr   normr   
rotary_embgradient_checkpointing	post_initrJ   s    `r&   r"   zOlmoModel.__init__8  s       !. +L):F<NPTP`aambbbb%H`BaBabbb
 
 "&"455	-V<<<&+# 	r'   N	input_idsre   r   r   inputs_embedsr   r   rh   r   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   )rA   input_embedsre   r   r   r   )re   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r	   rA   get_seq_lengthr/   arangerR   r   rz   r   r   r   r   r   r   )r$   r   re   r   r   r   r   r   rh   past_seen_tokensrv   r(   r   decoder_layers                 r&   r2   zOlmoModel.forwardH  s    -t";< 	[YZZZ *.*;*;I*F*FM 	?0*$+>>>O!CRC^==???de+0< "2]5H5K"KTaTh, , ,N )33A66L(;&))+%
 
 
 &"oom\JJ![)H4;+H)HI 		 		M)M*) /-$7   MM 		-00&++
 
 
 	
r'   )NNNNNNN)r3   r4   r5   r   r"   r   r   r   r/   r   r8   r   FloatTensorr   r   r   r   r2   r9   r:   s   @r&   r   r   6  s       z         151537+/5959$(8
 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 )OlmoForCausalLMzlm_head.weightlm_headcolwise_repr(   logitsc                     t                                          |           t          |          | _        |j        | _        t          j        |j        |j        d          | _        | 	                                 d S r>   )
r!   r"   r   r   r   rC   rD   r   r  r   rJ   s     r&   r"   zOlmoForCausalLM.__init__  sj       v&&
 +y!3V5FUSSS 	r'   Nr   r   re   r   r   r   labelsr   r   logits_to_keeprh   r   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, 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   re   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$   r   re   r   r   r   r  r   r   r  rh   outputsr(   slice_indicesr  r  s                   r&   r2   zOlmoForCausalLM.forward  s    @ ,64: 	,
)%+')	,
 	,
 	,
 	,
  18B>SV8W8Wk~ot444]kmAAA}aaa,?@AA%4%pVFt{OeppioppD%#3!/)
 
 
 	
r'   )	NNNNNNNNr   )r3   r4   r5   _tied_weights_keys_tp_plan_pp_planr"   r   r   r   r/   r   r8   r   r  r   r   r7   r   r   r   r2   r9   r:   s   @r&   r
  r
    sa       *+=)H_-z:;H      151537+/59-1$(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   )r`   )Nr   );typingr   r   r   r/   torch.nnrC   torch.nn.functionalrp   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   rx   r   r   r   r   r   r   r
  __all__r   r'   r&   <module>r,     s   - , , , , , , , , ,                 ! ! ! ! ! ! . . . . . . . . ) ) ) ) ) ) / / / / / / 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 & & & & & & I I I I I I I I I I 0 0 0 0 0 0 / / / / / / * * * * * *
 
 
 
 
BI 
 
 
    bi    ( ( (	UU\ 	U# 	U%, 	U 	U 	U 	U& % %I%<% 
% <	%
 U\*% % % '(% % % %42 2 2 28M) M) M) M) M)BI M) M) M)`* * * * *1 * * *Z         ")      F     /   $ K
 K
 K
 K
 K
# K
 K
 K
\ H
 H
 H
 H
 H
)? H
 H
 H
V B
A
Ar'   