+
    œ°³jý  ã                   óx   € R t ^ 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	# )
zOLMo model configuration)Ústrict)ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzallenai/OLMo-7B-hf)Ú
checkpointc                   óÞ   a a€ ] tR t^t oRtRtR.tRRRRRRRR	R
RRRRR	/tRR.R.3RRR.R.3RR.R.3/tRt	Rt
Rt^ t^ tRtRtRtRtRt^tRtRtRtRtRtRtRtV 3R ltV3R  ltR!tVtV ;t# )"Ú
OlmoConfigaô  
clip_qkv (`float`, *optional*):
    If not `None`, elements of query, key and value attention states are clipped so that their
    absolute value does not exceed this value.

```python
>>> from transformers import OlmoModel, OlmoConfig

>>> # Initializing a OLMo 7B style configuration
>>> configuration = OlmoConfig()

>>> # Initializing a model from the OLMo 7B style configuration
>>> model = OlmoModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```
ÚolmoÚpast_key_valueszlayers.*.self_attn.q_projÚcolwisezlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projÚrowwisezlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projÚembed_tokensÚ	input_idsÚinputs_embedsÚlayersÚhidden_statesÚattention_maskÚnormi€Ä  i   i +  NÚsilui   g{®Gáz”?TigÄ  Fg        c                óf   <€ V P                   f   V P                  V n         \        SV `  ! R/ VB  R # )N© )Únum_key_value_headsÚnum_attention_headsÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s   &,€Úl/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/olmo/configuration_olmo.pyr   ÚOlmoConfig.__post_init__V   s-   ø€ Ø×#Ñ#Ò+Ø'+×'?Ñ'?ˆDÔ$Ü‰ÒÑ' Ô'ó    c                ó†  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ R,          ;R&   S[;R&   S[ ;R	&   S[;R
&   S[;R&   S[ R,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[;R&   S[S[,          R,          ;R&   S[;R&   S[S[ ,          ;R&   S[R,          ;R&   # )é   Ú
vocab_sizeÚhidden_sizeÚintermediate_sizeÚnum_hidden_layersr   Nr   Ú
hidden_actÚmax_position_embeddingsÚinitializer_rangeÚ	use_cacheÚpad_token_idÚbos_token_idÚeos_token_idÚtie_word_embeddingsÚrope_parametersÚattention_biasÚattention_dropoutÚclip_qkv)ÚintÚstrÚfloatÚboolÚlistr   Údict)ÚformatÚ__classdict__s   "€r   Ú__annotate__ÚOlmoConfig.__annotate__   s>  ø‡ ‚ ñN ÑñO ñP ÑñQ ñR Ñ"ñS ñT ÑñU ñV Ñ!ñW ñX ˜t�Ñ*ñY ñZ Ññ[ ñ\ !Ñ'ñ] ñ^ Ñ#ñ_ ñ` Ñña ñb ˜•*Ñ ñc ñd ˜•*Ñ#ñe ñf ™™S�	•/ DÕ(Ñ0ñg ñh Ñ%ñi ñj $¡dÕ*¨TÕ1Ñ8ñk ñl Ñ ñm ñn ™s•{Ñ(ño ñp �d�lÑ!òq r    )r   ) Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planr#   r$   r%   r&   r   r   r'   r(   r)   r*   r+   r,   r-   r.   r/   r0   r1   r2   r   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r   r:   s   @@r   r   r      sò   ù‡ € ñð& €JØ#4Ð"5Ðà# YØ# YØ# YØ# YØ  )Ø 	Ø  )ðÐð 	˜+˜¨Ð(9Ð:Ø�OÐ%5Ð6¸Ð8IÐJØ�/Ð" _Ð$5Ð6ðÐð €JØ€KØ"ÐØÐØ!ÐØ&*ÐØ€JØ#'ÐØ#ÐØ€IØ €LØ#€LØ+0€LØ %ÐØ48€OØ €NØ%(ÐØ!€Hõ(÷u … r    r   N)rA   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r   Ú__all__r   r    r   Ú<module>rO      sJ   ðñ& å .å 3Ý 1Ý #ñ Ð/Ô0Øô;(Ð!ó ;(ó ó 1ð;(ð| ˆ.‚r    