
    Z j                     l    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
)    )strict   )PreTrainedConfig)RopeParameters)auto_docstringzallenai/Olmo2-7B-1124-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$'   S%r\
\\
   -  S-  \S&'   S'r\\S('   Sr\\-  S-  \S)'   S'r \\S*'   S+r!\\
-  \S,'   S-r"\\S.'   U 4S/ jr#S0r$U =r%$ )1Olmo2Config!   aU  
Example:

```python
>>> from transformers import Olmo2Model, Olmo2Config

>>> # Initializing a Olmo2 7B style configuration
>>> configuration = Olmo2Config()

>>> # Initializing a model from the Olmo2 7B style configuration
>>> model = Olmo2Model(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```
olmo2past_key_valuescolwise_gather_outputrowwise_split_input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_dropoutgh㈵>rms_norm_epsc                 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/olmo2/configuration_olmo2.pyr1   Olmo2Config.__post_init__Z   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-   r1   __static_attributes____classcell__)r4   s   @r5   r
   r
   !   sZ   " 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{(L%( (r7   r
   N)
huggingface_hub.dataclassesr   configuration_utilsr   modeling_rope_utilsr   utilsr   r
   __all__r/   r7   r5   <module>rO      sG   4 / 3 1 # 56:(" :(  7:(z /r7   