Ë
    ÛÓ^jÚ6  ã                   óÆ  — d Z ddl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
 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mZmZ ddlmZmZ ddlmZmZmZm Z m!Z!m"Z" ddl#m$Z$  ejJ                  e&«      Z' G d„ dejP                  «      Z) G d„ de!«      Z*d„ Z+d$d„Z, G d„ de«      Z-e G d„ de«      «       Z. G d„ de
«      Z/ G d„ d e «      Z0 G d!„ d"e«      Z1g d#¢Z2y)%zPyTorch Cohere model.é    )ÚCallableN)Únné   )ÚCache)ÚFlashAttentionKwargs)ÚGradientCheckpointingLayer)ÚBaseModelOutputWithPastÚCausalLMOutputWithPast)Údynamic_rope_update)ÚALL_ATTENTION_FUNCTIONS)ÚUnpack)ÚTransformersKwargsÚauto_docstringÚcan_return_tupleÚlogging)Úmaybe_autocastÚno_inherit_decoratoré   )ÚLlamaAttentionÚLlamaForCausalLMÚLlamaMLPÚ
LlamaModelÚLlamaRotaryEmbeddingÚeager_attention_forwardé   )ÚCohereConfigc                   ó&   ‡ — e Zd Zdˆ fd„	Zd„ Zˆ xZS )ÚCohereLayerNormc                 óŠ   •— t         ‰| �  «        t        j                  t	        j
                  |«      «      | _        || _        y)zcThe hidden size can be a tuple or an int. The tuple is used for QKNorm to normalize across head_dimN)ÚsuperÚ__init__r   Ú	ParameterÚtorchÚonesÚweightÚvariance_epsilon)ÚselfÚhidden_sizeÚepsÚbiasÚ	__class__s       €út/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/cohere/modular_cohere.pyr!   zCohereLayerNorm.__init__5   s/   ø€ ä‰ÑÔÜ—l‘l¤5§:¡:¨kÓ#:Ó;ˆŒØ #ˆÕó    c                 ó’  — |j                   }|j                  t        j                  «      }|j	                  dd¬«      }||z
  j                  d«      j	                  dd¬«      }||z
  t        j                  || j                  z   «      z  }| j                  j                  t        j                  «      |z  }|j                  |«      S )NéÿÿÿÿT)Úkeepdimr   )	ÚdtypeÚtor#   Úfloat32ÚmeanÚpowÚrsqrtr&   r%   )r'   Úhidden_statesÚinput_dtyper4   Úvariances        r,   ÚforwardzCohereLayerNorm.forward;   sª   € Ø#×)Ñ)ˆØ%×(Ñ(¬¯©Ó7ˆØ×!Ñ! "¨dÐ!Ó3ˆØ! DÑ(×-Ñ-¨aÓ0×5Ñ5°bÀ$Ð5ÓGˆØ&¨Ñ-´·±¸XÈ×H]ÑH]Ñ=]Ó1^Ñ^ˆØŸ™Ÿ™¤u§}¡}Ó5¸ÑEˆØ×Ñ Ó,Ð,r-   )Ngñhãˆµøä>F)Ú__name__Ú
__module__Ú__qualname__r!   r:   Ú__classcell__©r+   s   @r,   r   r   4   s   ø„ õ$ö-r-   r   c                   óD   — e Zd Z ej                  «       ed„ «       «       Zy)ÚCohereRotaryEmbeddingc                 ó  — | j                   d d d …d f   j                  «       j                  |j                  d   dd«      }|d d …d d d …f   j                  «       }t	        |j
                  j                  t        «      r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d¬«      5  |j                  «       |j                  «       z  j                  dd«      }t        j                  |dd¬	«      }|j                  «       | j                  z  }|j                  «       | j                  z  }	d d d «       j                  |j                   ¬
«      	j                  |j                   ¬
«      fS # 1 sw Y   ŒAxY w)Nr   r/   r   ÚmpsÚcpuF)Údevice_typeÚenabledr   ©Údim©r1   )Úinv_freqÚfloatÚexpandÚshapeÚ
isinstanceÚdeviceÚtypeÚstrr   Ú	transposer#   Úrepeat_interleaveÚcosÚattention_scalingÚsinr2   r1   )
r'   ÚxÚposition_idsÚinv_freq_expandedÚposition_ids_expandedrE   ÚfreqsÚembrT   rV   s
             r,   r:   zCohereRotaryEmbedding.forwardF   s@  € ð !ŸM™M¨$²°4¨-Ñ8×>Ñ>Ó@×GÑGÈ×HZÑHZÐ[\ÑH]Ð_aÐcdÓeÐØ ,ªQ°²a¨ZÑ 8× >Ñ >Ó @Ðä'1°!·(±(·-±-ÄÔ'EÈ!Ï(É(Ï-É-Ð[`ÒJ`�a—h‘h—m’mÐfkˆÜ¨¸UÔCñ 	5Ø&×,Ñ,Ó.Ð1F×1LÑ1LÓ1NÑN×YÑYÐZ[Ð]^Ó_ˆEÜ×)Ñ)¨%°¸Ô;ˆCØ—'‘'“)˜d×4Ñ4Ñ4ˆCØ—'‘'“)˜d×4Ñ4Ñ4ˆC÷		5ð �v‰v˜AŸG™GˆvÓ$ c§f¡f°1·7±7 fÓ&;Ð;Ð;÷	5ð 	5ús   Â=BFÆF
N)r;   r<   r=   r#   Úno_gradr   r:   © r-   r,   rA   rA   E   s$   „ Ø€U‡]�]ƒ_Øñ<ó ó ñ<r-   rA   c                 ó€   — | dd d d…f   }| ddd d…f   }t        j                  | |gd¬«      j                  d«      }|S )N.r   r   r/   rG   éþÿÿÿ)r#   ÚstackÚflatten)rW   Úx1Úx2Úrot_xs       r,   Úrotate_halfrf   V   sL   € à	
ˆ3‘�!�ˆ8‰€BØ	
ˆ3���1�ˆ9‰€BÜ�K‰K˜"˜˜b˜	 rÔ*×2Ñ2°2Ó6€EØ€Lr-   c                 ó6  — | j                   }| 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.
    rI   )r1   rK   Ú	unsqueezerf   r2   )ÚqÚkrT   rV   Úunsqueeze_dimr1   Úq_embedÚk_embeds           r,   Úapply_rotary_pos_embrn   ^   sŽ   € ð$ �G‰G€EØ	�‰‹	€AØ	�‰‹	€AØ
�-‰-˜Ó
&€CØ
�-‰-˜Ó
&€CØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�:‰:˜Eˆ:Ó" G§J¡J°U JÓ$;Ð;Ð;r-   c                   ó   ‡ — e Zd Zˆ fd„Zˆ xZS )Ú	CohereMLPc                 óJ  •— t         ‰| �  |«       t        j                  | j                  | j
                  d¬«      | _        t        j                  | j                  | j
                  d¬«      | _        t        j                  | j
                  | j                  d¬«      | _        y )NF)r*   )	r    r!   r   ÚLinearr(   Úintermediate_sizeÚ	gate_projÚup_projÚ	down_proj©r'   Úconfigr+   s     €r,   r!   zCohereMLP.__init__{   ss   ø€ Ü‰Ñ˜Ô ÜŸ™ 4×#3Ñ#3°T×5KÑ5KÐRWÔXˆŒÜ—y‘y ×!1Ñ!1°4×3IÑ3IÐPUÔVˆŒÜŸ™ 4×#9Ñ#9¸4×;KÑ;KÐRWÔXˆ�r-   )r;   r<   r=   r!   r>   r?   s   @r,   rp   rp   z   s   ø„ ÷Yð Yr-   rp   c                   óü   ‡ — e Zd ZdZddededz  fˆ fd„Z	 ddej                  de	ej                  ej                  f   dej                  dz  d	e
dz  d
ee   de	ej                  ej                  dz  f   fd„Zˆ xZS )ÚCohereAttentionz=Multi-headed attention from 'Attention Is All You Need' paperNrx   Ú	layer_idxc                 ó*  •— t         ‰| �  ||«       |j                  | _        | j                  ret        |j                  | j
                  f|j                  ¬«      | _        t        |j                  | j
                  f|j                  ¬«      | _	        y y ©N©r(   r)   )
r    r!   Úuse_qk_normr   Únum_attention_headsÚhead_dimÚlayer_norm_epsÚq_normÚnum_key_value_headsÚk_norm©r'   rx   r{   r+   s      €r,   r!   zCohereAttention.__init__†   s|   ø€ Ü‰Ñ˜ Ô+Ø!×-Ñ-ˆÔØ×Òä)Ø#×7Ñ7¸¿¹ÐGÈV×MbÑMbôˆDŒKô *Ø#×7Ñ7¸¿¹ÐGÈV×MbÑMbôˆD�Kð r-   r7   Úposition_embeddingsÚattention_maskÚpast_key_valuesÚkwargsÚreturnc                 ór  — |j                   d d }g |¢d‘| j                  ‘­}| j                  |«      j                  |«      }| j	                  |«      j                  |«      }	| j                  |«      j                  |«      }
| j                  r"| j                  |«      }| j                  |	«      }	|j                  dd«      }|	j                  dd«      }	|
j                  dd«      }
|\  }}t        ||	||«      \  }}	|� |j                  |	|
| j                  «      \  }	}
t        j                  | j                  j                   t"        «      } || ||	|
|f| j$                  sdn| j&                  | j(                  dœ|¤Ž\  }} |j*                  g |¢d‘­Ž j-                  «       }| j/                  |«      }||fS )Nr/   r   r   g        )ÚdropoutÚscaling)rM   r�   Úq_projÚviewÚk_projÚv_projr   rƒ   r…   rR   rn   Úupdater{   r   Úget_interfacerx   Ú_attn_implementationr   ÚtrainingÚattention_dropoutrŽ   ÚreshapeÚ
contiguousÚo_proj)r'   r7   r‡   rˆ   r‰   rŠ   Úinput_shapeÚhidden_shapeÚquery_statesÚ
key_statesÚvalue_statesrT   rV   Úattention_interfaceÚattn_outputÚattn_weightss                   r,   r:   zCohereAttention.forward’   sÂ  € ð $×)Ñ)¨#¨2Ð.ˆØ8˜Ð8 bÐ8¨$¯-©-Ñ8ˆà—{‘{ =Ó1×6Ñ6°|ÓDˆØ—[‘[ Ó/×4Ñ4°\ÓBˆ
Ø—{‘{ =Ó1×6Ñ6°|ÓDˆà×ÒØŸ;™; |Ó4ˆLØŸ™ ZÓ0ˆJà#×-Ñ-¨a°Ó3ˆØ×)Ñ)¨!¨QÓ/ˆ
Ø#×-Ñ-¨a°Ó3ˆà&‰ˆˆSÜ#7¸ÀjÐRUÐWZÓ#[Ñ ˆ�jàÐ&Ø'6×'=Ñ'=¸jÈ,ÐX\×XfÑXfÓ'gÑ$ˆJ˜ä(?×(MÑ(MØ�K‰K×,Ñ,Ô.Eó)
Ðñ %8ØØØØØð	%
ð  $Ÿ}š}‘C°$×2HÑ2HØ—L‘Lñ	%
ð ñ	%
Ñ!ˆ�\ð *�k×)Ñ)Ð;¨;Ð;¸Ò;×FÑFÓHˆØ—k‘k +Ó.ˆØ˜LÐ(Ð(r-   ©N)r;   r<   r=   Ú__doc__r   Úintr!   r#   ÚTensorÚtupler   r   r   r:   r>   r?   s   @r,   rz   rz   ‚   s¡   ø„ áGñ
˜|ð 
¸¸d¹
õ 
ð" )-ñ.)à—|‘|ð.)ð # 5§<¡<°·±Ð#=Ñ>ð.)ð Ÿ™ tÑ+ð	.)ð
  ™ð.)ð Ð-Ñ.ð.)ð 
ˆu�|‰|˜UŸ\™\¨DÑ0Ð0Ñ	1÷.)r-   rz   c                   óD  ‡ — e Zd Zdedefˆ fd„Z	 	 	 	 	 ddej                  dej                  dz  dej                  dz  de	dz  d	e
dz  d
eej                  ej                  f   dz  dee   deej                  eej                  ej                  f   dz  f   fd„Zˆ xZS )ÚCohereDecoderLayerrx   r{   c                 óÔ   •— t         ‰| �  «        |j                  | _        t        ||¬«      | _        t        |«      | _        t        |j                  |j                  ¬«      | _	        y )N)rx   r{   r~   )
r    r!   r(   rz   Ú	self_attnrp   Úmlpr   r‚   Úinput_layernormr†   s      €r,   r!   zCohereDecoderLayer.__init__Ä   sR   ø€ Ü‰ÑÔØ!×-Ñ-ˆÔÜ(°À)ÔLˆŒÜ˜VÓ$ˆŒÜ.¸F×<NÑ<NÐU[×UjÑUjÔkˆÕr-   Nr7   rˆ   rX   r‰   Ú	use_cacher‡   rŠ   r‹   c           
      ó–   — |}| j                  |«      } | j                  d||||||dœ|¤Ž\  }	}
| j                  |«      }||	z   |z   }|S )a¼  
        Args:
            hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
            attention_mask (`torch.FloatTensor`, *optional*):
                attention mask of size `(batch_size, sequence_length)` if flash attention is used or `(batch_size, 1,
                query_sequence_length, key_sequence_length)` if default attention is used.
            past_key_values (`Cache`, *optional*): cached past key and value projection states
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
            use_cache (`bool`, *optional*):
                If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
                (see `past_key_values`).
            position_embeddings (`tuple[torch.FloatTensor, torch.FloatTensor]`, *optional*):
                Tuple containing the cosine and sine positional embeddings of shape `(batch_size, seq_len, head_dim)`,
                with `head_dim` being the embedding dimension of each attention head.
        )r7   rˆ   rX   r‰   r®   r‡   r^   )r­   r«   r¬   )r'   r7   rˆ   rX   r‰   r®   r‡   rŠ   ÚresidualÚhidden_states_attentionÚ_Úhidden_states_mlps               r,   r:   zCohereDecoderLayer.forwardË   sx   € ð6 !ˆØ×,Ñ,¨]Ó;ˆà%3 T§^¡^ð &
Ø'Ø)Ø%Ø+ØØ 3ñ&
ð ñ&
Ñ"Ð ð !ŸH™H ]Ó3ÐØ Ð#:Ñ:Ð=NÑNˆØÐr-   )NNNFN)r;   r<   r=   r   r¥   r!   r#   r¦   Ú
LongTensorr   Úboolr§   r   r   ÚFloatTensorr:   r>   r?   s   @r,   r©   r©   Ã   sæ   ø„ ðl˜|ð l¸õ lð /3Ø04Ø(,Ø!&ØHLñ*à—|‘|ð*ð Ÿ™ tÑ+ð*ð ×&Ñ&¨Ñ-ð	*ð
  ™ð*ð ˜$‘;ð*ð # 5§<¡<°·±Ð#=Ñ>ÀÑEð*ð Ð-Ñ.ð*ð 
ˆu× Ñ  %¨×(9Ñ(9¸5×;LÑ;LÐ(LÑ"MÐPTÑ"TÐTÑ	U÷*r-   r©   c                   ó$   ‡ — e Zd Zdefˆ fd„Zˆ xZS )ÚCohereModelrx   c           	      ó  •— t         ‰| �  |«       t        j                  t	        |j
                  «      D �cg c]  }t        ||«      ‘Œ c}«      | _        t        |j                  |j                  ¬«      | _        y c c}w r}   )r    r!   r   Ú
ModuleListÚrangeÚnum_hidden_layersr©   Úlayersr   r(   r‚   Únormr†   s      €r,   r!   zCohereModel.__init__ù   sc   ø€ Ü‰Ñ˜Ô Ü—m‘mÜDIÈ&×JbÑJbÓDcÖd°yÔ ¨	Õ2Òdó
ˆŒô $°×1CÑ1CÈ&×J_ÑJ_Ô`ˆ�	ùò es   ·A=)r;   r<   r=   r   r!   r>   r?   s   @r,   r¸   r¸   ø   s   ø„ ða˜|÷ añ ar-   r¸   c                   ó"  ‡ — e Zd Zˆ fd„Zee	 	 	 	 	 	 	 	 ddej                  dz  dej                  dz  dej                  dz  de	dz  dej                  dz  dej                  dz  d	edz  d
eej                  z  dee   defd„«       «       Zˆ xZS )ÚCohereForCausalLMc                 óˆ   •— t         ‰| �  |«       t        |«      | _        |j                  | _        |j
                  | _        y r£   )r    r!   r¸   ÚmodelÚlogit_scaleÚtie_word_embeddingsrw   s     €r,   r!   zCohereForCausalLM.__init__  s8   ø€ Ü‰Ñ˜Ô Ü  Ó(ˆŒ
Ø!×-Ñ-ˆÔØ#)×#=Ñ#=ˆÕ r-   NÚ	input_idsrˆ   rX   r‰   Úinputs_embedsÚlabelsr®   Úlogits_to_keeprŠ   r‹   c	           
      ó–  —  | j                   d||||||dœ|	¤Ž}
|
j                  }t        |t        «      rt	        | d«      n|}| j                  |dd…|dd…f   «      }|| j                  z  }d}|�* | j                  d||| j                  j                  dœ|	¤Ž}t        |||
j                  |
j                  |
j                  ¬«      S )aÕ  
        Example:

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

        >> model = CohereForCausalLM.from_pretrained("CohereForAI/c4ai-command-r-v01")
        >> tokenizer = AutoTokenizer.from_pretrained("CohereForAI/c4ai-command-r-v01")

        >> 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."
        ```)rÅ   rˆ   rX   r‰   rÆ   r®   N)ÚlogitsrÇ   Ú
vocab_size)ÚlossrÊ   r‰   r7   Ú
attentionsr^   )rÂ   Úlast_hidden_staterN   r¥   ÚsliceÚlm_headrÃ   Úloss_functionrx   rË   r
   r‰   r7   rÍ   )r'   rÅ   rˆ   rX   r‰   rÆ   rÇ   r®   rÈ   rŠ   Úoutputsr7   Úslice_indicesrÊ   rÌ   s                  r,   r:   zCohereForCausalLM.forward  sé   € ð> ,6¨4¯:©:ð ,
ØØ)Ø%Ø+Ø'Øñ,
ð ñ,
ˆð  ×1Ñ1ˆÜ8BÀ>ÔSVÔ8Wœ˜~˜o¨tÔ4Ð]kˆØ—‘˜mªA¨}ºaÐ,?Ñ@ÓAˆØ˜$×*Ñ*Ñ*ˆàˆØÐØ%�4×%Ñ%Ðp¨V¸FÈtÏ{É{×OeÑOeÑpÐioÑpˆDä%ØØØ#×3Ñ3Ø!×/Ñ/Ø×)Ñ)ô
ð 	
r-   )NNNNNNNr   )r;   r<   r=   r!   r   r   r#   r´   r¦   r   r¶   rµ   r¥   r   r   r
   r:   r>   r?   s   @r,   rÀ   rÀ     sì   ø„ ô>ð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ñ6
à×#Ñ# dÑ*ð6
ð Ÿ™ tÑ+ð6
ð ×&Ñ&¨Ñ-ð	6
ð
  ™ð6
ð ×(Ñ(¨4Ñ/ð6
ð × Ñ  4Ñ'ð6
ð ˜$‘;ð6
ð ˜eŸl™lÑ*ð6
ð Ð+Ñ,ð6
ð 
 ò6
ó ó ô6
r-   rÀ   )rÀ   r¸   ÚCoherePreTrainedModel)r   )3r¤   Úcollections.abcr   r#   r   Úcache_utilsr   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   Úmodeling_outputsr	   r
   Úmodeling_rope_utilsr   Úmodeling_utilsr   Úprocessing_utilsr   Úutilsr   r   r   r   Úutils.genericr   r   Úllama.modeling_llamar   r   r   r   r   r   Úconfiguration_coherer   Ú
get_loggerr;   ÚloggerÚModuler   rA   rf   rn   rp   rz   r©   r¸   rÀ   Ú__all__r^   r-   r,   ú<module>rå      sÖ   ðñ, å $ã Ý å  Ý BÝ 9ß OÝ 6Ý 5Ý &ß RÓ Rß A÷÷ õ /ð 
ˆ×	Ñ	˜HÓ	%€ô-�b—i‘iô -ô"<Ð0ô <ò"ó<ô8Y�ô Yð ô=)�nó =)ó ð=)ô@2Ð3ô 2ôja�*ô aô?
Ð(ô ?
òD�r-   