
    Z j                     p    S r SSKJr  SSKJr  SSKJr  SSKJr  \" SS9\ " S	 S
\5      5       5       r	S
/r
g)zOLMo model configuration    )strict   )PreTrainedConfig)RopeParameters)auto_docstringzallenai/OLMo-7B-hf)
checkpointc                     ^  \ rS rSr% SrSrS/rSSSSSSSS.rS/S	/4S
S/S
/4S
/S
/4S.rSr	\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
S-  \S'   Sr\\S'   Sr\
\S'   Sr\\S'   Sr\\S'   S r\
S-  \S!'   Sr\
S-  \S"'   S#r\
\\
   -  S-  \S$'   S%r\\S&'   Sr\\-  S-  \S''   S%r \\S('   S)r!\\
-  \S*'   Sr"\S-  \S+'   U 4S, jr#S-r$U =r%$ ).
OlmoConfig   a  
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
```
olmopast_key_valuescolwise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_proj	input_idsinputs_embedshidden_statesattention_mask)embed_tokenslayersnormi  
vocab_sizei   hidden_sizei +  intermediate_size    num_hidden_layersnum_attention_headsNnum_key_value_headssilu
hidden_acti   max_position_embeddingsg{Gz?initializer_rangeT	use_cache   pad_token_idbos_token_idig  eos_token_idFtie_word_embeddingsrope_parametersattention_biasg        attention_dropoutclip_qkvc                 b   > U R                   c  U R                  U l         [        TU ]  " S0 UD6  g )N )r   r   super__post_init__)selfkwargs	__class__s     |/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/olmo/configuration_olmo.pyr/   OlmoConfig.__post_init__V   s-    ##+'+'?'?D$''    )r   )&__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr   int__annotations__r   r   r   r   r   r   strr    r!   floatr"   boolr$   r%   r&   listr'   r(   r   dictr)   r*   r+   r/   __static_attributes____classcell__)r2   s   @r3   r
   r
      s^   & J#4"5%.%.%.%."+ )"+ &(9:#%568IJ!"_$56 JK"s"s!!&*t*J#'S'#u#It L#* #L#*#+0L#S	/D(0 %%48O^d*T18 ND %(us{(!Hedl!( (r5   r
   N)r:   huggingface_hub.dataclassesr   configuration_utilsr   modeling_rope_utilsr   utilsr   r
   __all__r-   r5   r3   <module>rM      sJ   &  . 3 1 # /0;(! ;(  1;(| .r5   