o
    }oi                     @   s6   d dl m  mZ d dlmZmZ dd Zdd ZdS )    N)Baichuan2ConfigBaichuan2Config7Bc                  C   s   t dddd} | jdksJ | jtjksJ | jdu sJ | jdu s$J | jdks+J | jdks2J | j	dks9J | j
d	ks@J | jd	ksGJ | jdu sNJ d S )
N       )
num_layershidden_sizenum_attention_headsRMSNormTFg{Gz?gư>g        )r   normalizationactivation_funcFsilugated_linear_unitadd_bias_linear
seq_lengthinit_method_stdlayernorm_epsilonhidden_dropoutattention_dropout#share_embeddings_and_output_weightsconfig r   a/home/ubuntu/.local/lib/python3.10/site-packages/tests/collections/llm/gpt/model/test_baichuan.pytest_baichuan2_config   s   r   c                  C   sP   t  } | jdks
J | jdksJ | jdksJ | jdksJ | jdks&J d S )Nr   r   i +  )r   r   r   r   num_query_groupsffn_hidden_sizer   r   r   r   test_baichuan2_config_7b"   s   r   )	torch.nn.functionalnn
functionalr   'nemo.collections.llm.gpt.model.baichuanr   r   r   r   r   r   r   r   <module>   s   