+
    œ°³j!  ã                   ót   € ^ RI Ht ^RIHt ^RIHt ^RIHt ]! RR7      ] ! R R]4      4       4       tR.t	R	# )
é    )Ústrict)ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzUsefulSensors/moonshine-tiny)Ú
checkpointc                   óÀ   a a€ ] tR t^t oRtRtR.tRRRRRR	R
R/tRtRt	Rt
^t^t^t^tRtRtRtRtRtRtRt^tRtRtRtRtRt^t^tRtRtV 3R lt V3R lt!Rt"Vt#V ;t$# )ÚMoonshineConfiga	  
encoder_num_key_value_heads (`int`, *optional*):
    This is the number of key_value heads that should be used to implement Grouped Query Attention. If
    `encoder_num_key_value_heads=encoder_num_attention_heads`, the model will use Multi Head Attention (MHA), if
    `encoder_num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
    converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
    by meanpooling all the original heads within that group. For more details, check out [this
    paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to
    `num_attention_heads`.
decoder_num_key_value_heads (`int`, *optional*):
    This is the number of key_value heads that should be used to implement Grouped Query Attention. If
    `decoder_num_key_value_heads=decoder_num_attention_heads`, the model will use Multi Head Attention (MHA), if
    `decoder_num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
    converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
    by meanpooling all the original heads within that group. For more details, check out [this
    paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to
    `decoder_num_attention_heads`.
pad_head_dim_to_multiple_of (`int`, *optional*):
    Pad head dimension in encoder and decoder to the next multiple of this value. Necessary for using certain
    optimized attention implementations.
encoder_hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
    The non-linear activation function (function or string) in the encoder.
decoder_hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
    The non-linear activation function (function or string) in the decoder.

Example:

```python
>>> from transformers import MoonshineModel, MoonshineConfig

>>> # Initializing a Moonshine style configuration
>>> configuration = MoonshineConfig().from_pretrained("UsefulSensors/moonshine-tiny")

>>> # Initializing a model from the configuration
>>> model = MoonshineModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```Ú	moonshineÚpast_key_valuesÚnum_key_value_headsÚdecoder_num_key_value_headsÚnum_attention_headsÚdecoder_num_attention_headsÚnum_hidden_layersÚdecoder_num_hidden_layersÚ
hidden_actÚdecoder_hidden_acti €  i   i€  NÚgeluÚsilui   g{®Gáz”?TFg        c                óÈ   <€ V P                   f   V P                  V n         V P                  f   V P                  V n        VP	                  RR4       \
        SV `  ! R/ VB  R # )NÚpartial_rotary_factorgÍÌÌÌÌÌì?© )Úencoder_num_key_value_headsÚencoder_num_attention_headsr   r   Ú
setdefaultÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s   &,€Úv/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/moonshine/configuration_moonshine.pyr   ÚMoonshineConfig.__post_init__i   sX   ø€ Ø×+Ñ+Ò3Ø/3×/OÑ/OˆDÔ,à×+Ñ+Ò3Ø/3×/OÑ/OˆDÔ,à×ÑÐ1°3Ô7Ü‰ÒÑ' Ô'ó    c                óÜ  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ R,          ;R	&   S[ R,          ;R
&   S[ R,          ;R&   S[;R&   S[;R&   S[ ;R&   S[;R&   S[ ;R&   S[;R&   S[S[,          R,          ;R&   S[;R&   S[;R&   S[S[ ,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[ R,          ;R&   S[;R&   # )é   Ú
vocab_sizeÚhidden_sizeÚintermediate_sizeÚencoder_num_hidden_layersr   r   r   Nr   r   Úpad_head_dim_to_multiple_ofÚencoder_hidden_actr   Úmax_position_embeddingsÚinitializer_rangeÚdecoder_start_token_idÚ	use_cacheÚrope_parametersÚis_encoder_decoderÚattention_biasÚattention_dropoutÚbos_token_idÚeos_token_idÚpad_token_idÚtie_word_embeddings)ÚintÚstrÚfloatÚboolr   ÚdictÚlist)ÚformatÚ__classdict__s   "€r!   Ú__annotate__ÚMoonshineConfig.__annotate__   sœ  ø‡ ‚ ñh Ññi ñj Ññk ñl Ñ!ñm ñn  #Ñ&ño ñp  #Ñ&ñq ñr "%Ñ(ñs ñt "%Ñ(ñu ñv "% t¥Ñ2ñw ñx "% t¥Ñ2ñy ñz "% t¥Ñ2ñ{ ñ| Ñ$ñ} ñ~ Ñ$ñ ñ@ !Ñ&ñA ñB Ñ#ñC ñD  Ñ#ñE ñF ÑñG ñH $¡dÕ*¨TÕ1Ñ8ñI ñJ Ñ#ñK ñL Ñ ñM ñN ™s•{Ñ(ñO ñP ˜•*Ñ ñQ ñR ™™S�	•/ DÕ(Ñ,ñS ñT ˜•*Ñ#ñU ñV Ñ$òW r#   )r   r   )%Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚattribute_mapr&   r'   r(   r)   r   r   r   r   r   r*   r+   r   r,   r-   r.   r/   r0   r1   r2   r3   r4   r5   r6   r7   r   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r    r?   s   @@r!   r	   r	      sÑ   ù‡ € ñ&ðP €JØ#4Ð"5ÐàÐ<ØÐ<ØÐ8ØÐ*ð	€Mð €JØ€KØ!ÐØ%&ÐØ%&ÐØ'(ÐØ'(ÐØ.2ÐØ.2ÐØ.2ÐØ$ÐØ$ÐØ#&ÐØ#ÐØ"#ÐØ€IØ48€OØ#ÐØ €NØ%(ÐØ €LØ+,€LØ#€LØ $Ðõ(÷[ … r#   r	   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r	   Ú__all__r   r#   r!   Ú<module>rS      sK   ðõ* /å 3Ý 1Ý #ñ Ð9Ô:ØôS(Ð&ó S(ó ó ;ðS(ðl Ð
‚r#   