# Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. """OLMoE model configuration""" from ...configuration_utils import PreTrainedConfig from ...modeling_rope_utils import RopeParameters class OlmoeConfig(PreTrainedConfig): r""" This is the configuration class to store the configuration of a [`OlmoeModel`]. It is used to instantiate an OLMoE 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/OLMoE-1B-7B-0924](https://huggingface.co/allenai/OLMoE-1B-7B-0924). 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 OLMoE model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`OlmoeModel`] hidden_size (`int`, *optional*, defaults to 2048): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 2048): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 16): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 16): 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 4096): 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. rms_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the rms normalization layers. 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_parameters (`RopeParameters`, *optional*): Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE with longer `max_position_embeddings`. 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. 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. num_experts_per_tok (`int`, *optional*, defaults to 8): Number of selected experts. num_experts (`int`, *optional*, defaults to 64): Number of routed experts. output_router_logits (`bool`, *optional*, defaults to `False`): Whether or not the router logits should be returned by the model. Enabling this will also allow the model to output the auxiliary loss, including load balancing loss and router z-loss. router_aux_loss_coef (`float`, *optional*, defaults to 0.01): The aux loss factor for the total loss. norm_topk_prob (`bool`, *optional*, defaults to `False`): Whether to normalize the topk probabilities. ```python >>> from transformers import OlmoeModel, OlmoeConfig >>> # Initializing a OLMoE 7B A1B style configuration >>> configuration = OlmoeConfig() >>> # Initializing a model from the OLMoE 7B A1B style configuration >>> model = OlmoeModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "olmoe" keys_to_ignore_at_inference = ["past_key_values"] attribute_map = {"num_local_experts": "num_experts"} def __init__( self, vocab_size: int | None = 50304, hidden_size: int | None = 2048, intermediate_size: int | None = 2048, num_hidden_layers: int | None = 16, num_attention_heads: int | None = 16, num_key_value_heads: int | None = None, hidden_act: str | None = "silu", max_position_embeddings: int | None = 4096, initializer_range: float | None = 0.02, rms_norm_eps: int | None = 1e-05, use_cache: bool | None = True, pad_token_id: int | None = 1, bos_token_id: int | None = None, eos_token_id: int | None = 50279, tie_word_embeddings: int | None = False, rope_parameters: RopeParameters | dict[str, RopeParameters] | None = None, attention_bias: bool | None = False, attention_dropout: float | None = 0.0, clip_qkv: bool | None = None, num_experts_per_tok: int | None = 8, num_experts: int | None = 64, output_router_logits: bool | None = False, router_aux_loss_coef: float | None = 0.01, norm_topk_prob: bool | None = False, **kwargs, ): self.vocab_size = vocab_size self.max_position_embeddings = max_position_embeddings self.hidden_size = hidden_size self.intermediate_size = intermediate_size self.num_hidden_layers = num_hidden_layers self.num_attention_heads = num_attention_heads # for backward compatibility if num_key_value_heads is None: num_key_value_heads = num_attention_heads self.num_key_value_heads = num_key_value_heads self.hidden_act = hidden_act self.initializer_range = initializer_range self.rms_norm_eps = rms_norm_eps self.use_cache = use_cache self.attention_bias = attention_bias self.attention_dropout = attention_dropout self.clip_qkv = clip_qkv self.num_experts_per_tok = num_experts_per_tok self.num_experts = num_experts self.output_router_logits = output_router_logits self.router_aux_loss_coef = router_aux_loss_coef self.norm_topk_prob = norm_topk_prob self.rope_parameters = rope_parameters self.tie_word_embeddings = tie_word_embeddings self.pad_token_id = pad_token_id self.bos_token_id = bos_token_id self.eos_token_id = eos_token_id super().__init__(**kwargs) __all__ = ["OlmoeConfig"]