Ë
    ÜÓ^j»  ã                   ór   — d dl mZ ddlmZ ddlmZ ddlmZ  ed¬«      e G d„ d	e«      «       «       Zd	gZ	y
)é    )Ústricté   )ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzallenai/Olmo-3-7B-Instruct)Ú
checkpointc                   óÒ  ‡ — e Zd ZU dZdZdgZddddddddœZd	gd
gfddgdgfdgdgfdœZdZe	e
d<   dZe	e
d<   dZe	e
d<   dZe	e
d<   dZe	e
d<   dZe	dz  e
d<   dZee
d<   dZe	e
d<   dZee
d<   dZee
d <   d!Ze	dz  e
d"<   dZe	dz  e
d#<   d$Ze	ee	   z  dz  e
d%<   d&Zee
d'<   dZeez  dz  e
d(<   d&Zee
d)<   d*Z ee	z  e
d+<   d,Z!ee
d-<   d.Z"dZ#e	dz  e
d/<   dZ$ee   dz  e
d0<   ˆ fd1„Z%d2„ Z&ˆ xZ'S )3ÚOlmo3Configa�  
    Example:

    ```python
    >>> from transformers import Olmo3Model, Olmo3Config

    >>> # Initializing a Olmo3 7B style configuration
    >>> configuration = Olmo3Config()

    >>> # Initializing a model from the Olmo3 7B style configuration
    >>> model = Olmo3Model(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```
    Úolmo3Úpast_key_valuesÚcolwise_gather_outputÚrowwise_split_inputÚcolwiseÚrowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projÚ	input_idsÚinputs_embedsÚhidden_statesÚattention_mask)Úembed_tokensÚlayersÚnormi€Ä  Ú
vocab_sizei   Úhidden_sizei +  Úintermediate_sizeé    Únum_hidden_layersÚnum_attention_headsNÚnum_key_value_headsÚsiluÚ
hidden_acti   Úmax_position_embeddingsg{®Gáz”?Úinitializer_rangeTÚ	use_cacheé   Úpad_token_idÚbos_token_idigÄ  Úeos_token_idFÚtie_word_embeddingsÚrope_parametersÚattention_biasg        Úattention_dropoutgñhãˆµøä>Úrms_norm_epsg    €„AÚsliding_windowÚlayer_typesc                 ó$  •— | j                   €| j                  | _         | j                  €5t        | j                  «      D �cg c]  }|dz   dz  dk7  rdnd‘Œ c}| _        | j                   €| j                  | _         t        ‰| �  di |¤Ž y c c}w )Nr$   é   r   Úsliding_attentionÚfull_attention© )r   r   r.   Úranger   ÚsuperÚ__post_init__)ÚselfÚkwargsÚiÚ	__class__s      €úx/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/olmo3/configuration_olmo3.pyr6   zOlmo3Config.__post_init__Y   s”   ø€ Ø×#Ñ#Ð+Ø'+×'?Ñ'?ˆDÔ$à×ÑÐ#äW\Ð]a×]sÑ]sÓWtö ØRS¨¨A©°¡{°aÒ'7Ñ#Ð=MÑMò ˆDÔð ×#Ñ#Ð+Ø'+×'?Ñ'?ˆDÔ$Ü‰ÑÑ' Ó'ùò s   ÁBc                 ón  — |j                  dd «      }ddiddidœ}| j                  �| j                  n|| _        |�| j                  d   j                  |«       | j                  j                  d«      €ddi| j                  d<   | j                  d   j	                  d|j                  d| j
                  «      «       | j                  j                  d«      €ddi| j                  d<   | j                  d   j	                  d|j                  d| j
                  «      «       | j                  «        |S )NÚrope_scalingÚ	rope_typeÚdefault)r1   r2   r2   Ú
rope_thetar1   )Úpopr)   ÚupdateÚgetÚ
setdefaultÚdefault_thetaÚstandardize_rope_params)r7   r8   r=   Údefault_rope_paramss       r;   Úconvert_rope_params_to_dictz'Olmo3Config.convert_rope_params_to_dicte   s:  € Ø—z‘z .°$Ó7ˆð
 #.¨yÐ!9Ø*¨IÐ6ñ
Ðð 8<×7KÑ7KÐ7W˜t×3Ò3Ð]pˆÔØÐ#Ø× Ñ Ð!1Ñ2×9Ñ9¸,ÔGð ×Ñ×#Ñ#Ð$4Ó5Ð=Ø6AÀ9Ð5MˆD× Ñ Ð!1Ñ2Ø×ÑÐ-Ñ.×9Ñ9¸,ÈÏ
É
ÐS_Ðae×asÑasÓHtÔuØ×Ñ×#Ñ#Ð$7Ó8Ð@Ø9DÀiÐ8PˆD× Ñ Ð!4Ñ5Ø×ÑÐ0Ñ1×<Ñ<Ø˜&Ÿ*™* \°4×3EÑ3EÓFô	
ð
 	×$Ñ$Ô&Øˆó    )(Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planr   ÚintÚ__annotations__r   r   r   r   r   r    Ústrr!   r"   Úfloatr#   Úboolr%   r&   r'   Úlistr(   r)   r   Údictr*   r+   r,   rE   r-   r.   r6   rH   Ú__classcell__)r:   s   @r;   r
   r
      s€  ø… ñð" €JØ#4Ð"5Ðà%<Ø%<Ø%<Ø%:Ø"+Ø )Ø"+ñÐð &˜¨Ð(9Ð:Ø#Ð%5Ð6¸Ð8IÐJØ!Ð" _Ð$5Ð6ñÐð €J�ÓØ€K�ÓØ"Ð�sÓ"ØÐ�sÓØ!Ð˜Ó!Ø&*Ð˜˜t™Ó*Ø€J�ÓØ#'Ð˜SÓ'Ø#Ð�uÓ#Ø€IˆtÓØ €L�#˜‘*Ó Ø#€L�#˜‘*Ó#Ø+0€L�#˜˜S™	‘/ DÑ(Ó0Ø %Ð˜Ó%Ø48€O�^ dÑ*¨TÑ1Ó8Ø €N�DÓ Ø%(Ð�u˜s‘{Ó(à€L�%ÓØ€Mà!%€N�C˜$‘JÓ%Ø$(€K��c‘˜TÑ!Ó(ô
(örI   r
   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r
   Ú__all__r3   rI   r;   ú<module>r_      sJ   ðõ* /å 3Ý 1Ý #ñ Ð7Ô8Øô`Ð"ó `ó ó 9ð`ðF ˆ/�rI   