§
    9²¸j"  ã                   ó�   — d dl mZ ddlmZmZ ddlmZ ddlmZ  ed¬¦  «        e G d„ d	e¦  «        ¦   «         ¦   «         Z	d	gZ
d
S )é    )Ústricté   )ÚPreTrainedConfigÚremap_legacy_layer_types)ÚRopeParameters)Úauto_docstringzZyphra/Zamba2-2.7B)Ú
checkpointc                   ó’  ‡ — e Zd ZU dZdZdddœZdg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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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e	d"<   d#Zee	d$<   d%Zee	d&<   d%Zee	d'<   dZedz  e	d(<   d)Z ee	d*<   d+Z!ee	d,<   dZ"edz  e	d-<   d.Z#eez  e	d/<   dZ$ee	d0<   d%Z%ee	d1<   d2Z&ee	d3<   d%Z'ee	d4<   dZ(e)e*z  dz  e	d5<   d6Z+ee	d7<   d8Z,ee	d9<   d Z-ee	d:<   dZ.ee	d;<   d<Z/edz  e	d=<   dZ0edz  e	d><   dZ1eee         z  dz  e	d?<   d%Z2ee	d@<   d Z3ee	dA<   ˆ fdB„Z4ˆ xZ5S )CÚZamba2Configað	  
    mamba_ngroups (`int`, *optional*, defaults to 1):
        Number of groups for the evolution matrices of mamba 2.
    n_mamba_heads (`int`, *optional*, defaults to 8):
        Number of heads for the evolution matrices of mamba 2.
    use_mamba_kernels (`bool`, *optional*, defaults to `True`):
        Flag indicating whether or not to use the fast mamba kernels.
    use_conv_bias (`bool`, *optional*, defaults to `True`):
        Whether or not to use bias in the convolution layer of the mixer block.
    chunk_size (`int`, *optional*, defaults to 256):
        Size of the chunks that will comprise the sequence.
    use_mem_eff_path (`bool`, *optional*, defaults to `False`):
        Whether or not to use the fused conv1d and scan in mamba2 layers.
    add_bias_linear (`bool`, *optional*, defaults to `False`):
        Flag indicating whether or not to use bias in various layers
    num_mem_blocks (`int`, *optional*, defaults to 1):
        Number of unshared transformer blocks.
    use_shared_attention_adapter (`bool`, *optional*, defaults to `False`):
        If True, unshared adapters (formally the same as LoRA but used in the base model) will be added to the q, k, v projectors in the shared attention layers.
    adapter_rank (`int`, *optional*, defaults to 128):
        Rank of the adapter in the shared MLP and shared attention layers.
    use_mem_rope (`bool`, *optional*, defaults to `False`):
        If True, includes RoPE in the shared attention layers.
    num_logits_to_keep (`int` or `None`, *optional*, defaults to 1):
        Number of prompt logits to calculate during generation. If `None`, all logits will be calculated. If an
        integer value, only last `num_logits_to_keep` logits will be calculated. Default is 1 because only the
        logits of the last prompt token are needed for generation. For long sequences, the logits for the entire
        sequence may use a lot of memory so, setting `num_logits_to_keep=1` will reduce memory footprint
        significantly.
    use_long_context (`bool`, *optional*, defaults to `False`):
        Activates the context-extended version of Zamba by modifying RoPE.

    Example:
    ```python
    >>> from transformers import Zamba2Model, Zamba2Config
    >>> # Initializing a Zamba2-2.7B style configuration
    >>> configuration = Zamba2Config()
    >>> # Initializing a model from the Zamba2-2.7B style configuration
    >>> model = Zamba2Model(configuration)
    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```Úzamba2Úlayers_block_typeÚattention_head_dim)Úlayer_typesÚhead_dimÚpast_key_valuesi }  Ú
vocab_sizei   Úmax_position_embeddingsi 
  Úhidden_sizeé6   Únum_hidden_layersNé@   Úmamba_d_stateé   Úmamba_d_convé   Úmamba_expandé   Úmamba_ngroupsgü©ñÒMbP?Útime_step_mingš™™™™™¹?Útime_step_maxg-Cëâ6?Útime_step_flooré   Ún_mamba_headsTÚuse_mamba_kernelsÚuse_conv_biasé   Ú
chunk_sizeFÚuse_mem_eff_pathÚadd_bias_linearÚintermediate_sizeÚgeluÚ
hidden_acté    Únum_attention_headsÚnum_key_value_headsg        Úattention_dropoutÚnum_mem_blocksÚuse_shared_attention_adapteré€   Úadapter_rankÚuse_mem_ropeÚrope_parametersg{®Gáz”?Úinitializer_rangegñhãˆµøä>Úrms_norm_epsÚ	use_cacheÚnum_logits_to_keepr   Úpad_token_idÚbos_token_idÚeos_token_idÚuse_long_contextÚtie_word_embeddingsc                 ót  •— | j         p	d| j        z  | _         d| j        z  | _        d| j        z  | j        z  | _        t          | j        | j        z  ¦  «        | j        z  | _        | j	        rd| _
        | j        €| j        | _        | j        | j        z  | _        | j        | _        | j        €4dgdgdz  dgz   dz  z   dgdz  z   dgz   dgdz  z   dgz   dgdz  z   | _        nt          | j        ¦  «        | _        d	„ t!          | j        ¦  «        D ¦   «         | _         t%          ¦   «         j        d
i |¤Ž d S )Nr   r   i @  Úlinear_attentioné   Úhybridé   r   c                 ó$   — g | ]\  }}|d k    ¯|‘ŒS )rC   © )Ú.0ÚindexÚtypes      ú/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/zamba2/configuration_zamba2.pyú
<listcomp>z.Zamba2Config.__post_init__.<locals>.<listcomp>Œ   s(   € Ð pÐ pÐ p©;¨5°$Ð_cÐgoÒ_oÐ_o Ð_oÐ_oÐ_oó    rF   )r*   r   Úattention_hidden_sizer.   r   Úintr   r#   Úmamba_headdimr>   r   r/   Úkv_channelsÚnum_query_groupsr   r   Ú	enumerateÚhybrid_layer_idsÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €rJ   rU   zZamba2Config.__post_init__p   sˆ  ø€ Ø!%Ô!7Ð!O¸1¸tÔ?OÑ;OˆÔØ%&¨Ô)9Ñ%9ˆÔ"Ø"# dÔ&6Ñ"6¸$Ô:RÑ"RˆÔÝ  Ô!2°TÔ5EÑ!EÑFÔFÈ$ÔJ\Ñ\ˆÔØÔ ð 	1Ø+0ˆDÔ(àÔ#Ð+Ø'+Ô'?ˆDÔ$àÔ+¨tÔ/GÑGˆÔØ $Ô 8ˆÔð Ô!Ð)à#Ð$Ø&Ð'¨!Ñ+¨x¨jÑ8¸AÑ=ñ>à%Ð&¨Ñ*ñ+ð �*ñð &Ð&¨Ñ*ñ	+ð
 �*ñð &Ð&¨Ñ*ñ+ð Ô"Ð"õ &>¸dÔ>TÑ%UÔ%UˆDÔ"Ø pÐ p½)ÀDÔDZÑ:[Ô:[Ð pÑ pÔ pˆÔØ�‰ŒÔÐ'Ð' Ð'Ð'Ð'Ð'Ð'rL   )6Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚattribute_mapÚkeys_to_ignore_at_inferencer   rN   Ú__annotations__r   r   r   r   ÚlistÚstrr   r   r   r   r   Úfloatr    r!   r#   r$   Úboolr%   r'   r(   r)   r*   r,   r.   r/   r0   r1   r2   r4   r5   r6   r   Údictr7   r8   r9   r:   r;   r<   r=   r>   r?   rU   Ú__classcell__)rX   s   @rJ   r   r      sõ  ø€ € € € € € ð)ð )ðV €JØ$7ÐEYÐZÐZ€MØ#4Ð"5Ðà€J�ÐÐÑØ#'Ð˜SÐ'Ð'Ñ'Ø€K�ÐÐÑØÐ�sÐÐÑØ*.Ð�t˜C”y 4Ñ'Ð.Ð.Ñ.Ø€M�3ÐÐÑØ€L�#ÐÐÑØ€L�#ÐÐÑØ€M�3ÐÐÑØ €M�5Ð Ð Ñ Ø€M�5ÐÐÑØ!€O�UÐ!Ð!Ñ!Ø€M�3ÐÐÑØ"Ð�tÐ"Ð"Ñ"Ø€M�4ÐÐÑØ€J�ÐÐÑØ"Ð�dÐ"Ð"Ñ"Ø!€O�TÐ!Ð!Ñ!Ø$(Ð�s˜T‘zÐ(Ð(Ñ(Ø€J�ÐÐÑØ!Ð˜Ð!Ð!Ñ!Ø&*Ð˜˜t™Ð*Ð*Ñ*Ø%(Ð�u˜s‘{Ð(Ð(Ñ(Ø€N�CÐÐÑØ).Ð  $Ð.Ð.Ñ.Ø€L�#ÐÐÑØ€L�$ÐÐÑØ48€O�^ dÑ*¨TÑ1Ð8Ð8Ñ8Ø#Ð�uÐ#Ð#Ñ#Ø€L�%ÐÐÑØ€IˆtÐÐÑØÐ˜ÐÐÑØ €L�#˜‘*Ð Ð Ñ Ø €L�#˜‘*Ð Ð Ñ Ø+,€L�#˜˜Sœ	‘/ DÑ(Ð,Ð,Ñ,Ø"Ð�dÐ"Ð"Ñ"Ø $Ð˜Ð$Ð$Ñ$ð(ð (ð (ð (ð (ð (ð (ð (ð (rL   r   N)Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   r   Úmodeling_rope_utilsr   Úutilsr   r   Ú__all__rF   rL   rJ   ú<module>rl      s¼   ðð" /Ð .Ð .Ð .Ð .Ð .à MÐ MÐ MÐ MÐ MÐ MÐ MÐ MØ 1Ð 1Ð 1Ð 1Ð 1Ð 1Ø #Ð #Ð #Ð #Ð #Ð #ð €Ð/Ð0Ñ0Ô0Øðs(ð s(ð s(ð s(ð s(Ð#ñ s(ô s(ñ „ñ 1Ô0ðs(ðl Ð
€€€rL   