
    cCi/                     <    S SK JrJr  S SKJr   " S S\5      rS/rg)   )PretrainedConfiglayer_type_validationrope_config_validationc                      ^  \ 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U 4S jjr	S r
SrU =r$ )Olmo3Config   aT  
This is the configuration class to store the configuration of a [`Olmo3Model`]. It is used to instantiate an OLMo3
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
defaults will yield a similar configuration to that of the [allenai/OLMo-3-0725-1B](https://huggingface.co/allenai/OLMo-3-0725-1B).

Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PretrainedConfig`] for more information.


Args:
    vocab_size (`int`, *optional*, defaults to 50304):
        Vocabulary size of the Olmo3 model. Defines the number of different tokens that can be represented by the
        `inputs_ids` passed when calling [`Olmo3Model`]
    hidden_size (`int`, *optional*, defaults to 4096):
        Dimension of the hidden representations.
    intermediate_size (`int`, *optional*, defaults to 11008):
        Dimension of the MLP representations.
    num_hidden_layers (`int`, *optional*, defaults to 32):
        Number of hidden layers in the Transformer decoder.
    num_attention_heads (`int`, *optional*, defaults to 32):
        Number of attention heads for each attention layer in the Transformer 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
        `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
        `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`.
    hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
        The non-linear activation function (function or string) in the decoder.
    max_position_embeddings (`int`, *optional*, defaults to 2048):
        The maximum sequence length that this model might ever be used with.
    initializer_range (`float`, *optional*, defaults to 0.02):
        The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
    use_cache (`bool`, *optional*, defaults to `True`):
        Whether or not the model should return the last key/values attentions (not used by all models). Only
        relevant if `config.is_decoder=True`.
    pad_token_id (`int`, *optional*, defaults to 1):
        Padding token id.
    bos_token_id (`int`, *optional*):
        Beginning of stream token id.
    eos_token_id (`int`, *optional*, defaults to 50279):
        End of stream token id.
    tie_word_embeddings (`bool`, *optional*, defaults to `False`):
        Whether to tie weight embeddings
    rope_theta (`float`, *optional*, defaults to 10000.0):
        The base period of the RoPE embeddings.
    rope_scaling (`Dict`, *optional*):
        Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
        and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
        accordingly.
        Expected contents:
            `rope_type` (`str`):
                The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
                'llama3'], with 'default' being the original RoPE implementation.
            `factor` (`float`, *optional*):
                Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
                most scaling types, a `factor` of x will enable the model to handle sequences of length x *
                original maximum pre-trained length.
            `original_max_position_embeddings` (`int`, *optional*):
                Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
                pretraining.
            `attention_factor` (`float`, *optional*):
                Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
                computation. If unspecified, it defaults to value recommended by the implementation, using the
                `factor` field to infer the suggested value.
            `beta_fast` (`float`, *optional*):
                Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
                ramp function. If unspecified, it defaults to 32.
            `beta_slow` (`float`, *optional*):
                Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
                ramp function. If unspecified, it defaults to 1.
            `short_factor` (`list[float]`, *optional*):
                Only used with 'longrope'. The scaling factor to be applied to short contexts (<
                `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
                size divided by the number of attention heads divided by 2
            `long_factor` (`list[float]`, *optional*):
                Only used with 'longrope'. The scaling factor to be applied to long contexts (<
                `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
                size divided by the number of attention heads divided by 2
            `low_freq_factor` (`float`, *optional*):
                Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
            `high_freq_factor` (`float`, *optional*):
                Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
    attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
        Whether to use a bias in the query, key, value and output projection layers during self-attention.
    attention_dropout (`float`, *optional*, defaults to 0.0):
        The dropout ratio for the attention probabilities.
    rms_norm_eps (`float`, *optional*, defaults to 1e-05):
        The epsilon used by the rms normalization layers.
    sliding_window (`int`, *optional*, defaults to 4096):
        Size of the sliding window for sliding window attention.
    layer_types (`list`, *optional*):
        Attention pattern for each layer. Defaults to sliding window attention
        for 3 out of 4 layers, and full attention for every 4th layer.

```python
>>> from transformers import Olmo3Model, Olmo3Config

>>> # Initializing a Olmo3 7B style configuration
>>> configuration = Olmo3Config()

>>> # Initializing a model from the Olmo3 7B style configuration
>>> model = Olmo3Model(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```
olmo3past_key_valuescolwise_reprowwise_rep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normc                   > [         TU ]  " SUUUUS.UD6  Xl        Xl        X l        X0l        X@l        XPl        Uc  UnX`l        Xpl	        Xl
        Xl        Xl        UU l        U R                  5         UU l        UU l        UU l        UU l        UU l        U R&                  c9  [)        U R                  5       Vs/ s H  nUS-   S-  S:w  a  SOSPM     snU l        [+        U R&                  5        g s  snf )N)pad_token_idbos_token_ideos_token_idtie_word_embeddings          sliding_attentionfull_attention )super__init__
vocab_sizemax_position_embeddingshidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsnum_key_value_heads
hidden_actinitializer_range	use_cache
rope_thetarope_scaling_rope_scaling_validationattention_biasattention_dropoutrms_norm_epssliding_windowlayer_typesranger   )selfr$   r&   r'   r(   r)   r*   r+   r%   r,   r-   r   r   r   r   r.   r/   r1   r2   r3   r4   r5   kwargsi	__class__s                           g/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/olmo3/configuration_olmo3.pyr#   Olmo3Config.__init__   s   2 	 	
%%% 3		

 	
 %'>$&!2!2#6  &"5#6 $!2"$(%%',!2(,&#W\]a]s]sWt WtRSA{a'7#=MMWt D 	d../ s   <C4c                     [        U 5        g)z,
Validate the `rope_scaling` configuration.
Nr   )r7   s    r;   r0   $Olmo3Config._rope_scaling_validation   s     	t$    )r1   r2   r+   r&   r,   r'   r5   r%   r)   r(   r*   r3   r/   r.   r4   r-   r$   )i     i +      rA   Nsilui   g{Gz?Tr   Nig  Fg     @NFg        gh㈵>r@   N)__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr#   r0   __static_attributes____classcell__)r:   s   @r;   r   r      s    m^ J#4"5%2%2%2%2"+ )"+ &(9:#%568IJ!"_$56   $!-=0~% %r?   r   N)configuration_utilsr   r   modeling_rope_utilsr   r   __all__r!   r?   r;   <module>rQ      s'   , K 9D%" D%N /r?   