from transformers.configuration_utils import PretrainedConfig class HyperQwen2Config(PretrainedConfig): r""" This is the configuration class to store the configuration of a [`Qwen2Model`]. It is used to instantiate a Qwen2 model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of Qwen2-7B-beta [Qwen/Qwen2-7B-beta](https://huggingface.co/Qwen/Qwen2-7B-beta). 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 151936): Vocabulary size of the Qwen2 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Qwen2Model`] hidden_size (`int`, *optional*, defaults to 4096): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 22016): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 32): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 32): Number of attention heads for each attention layer in the Transformer encoder. num_key_value_heads (`int`, *optional*, defaults to 32): 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 checkout [this paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`. 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 32768): 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-06): 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`. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether the model's input and output word embeddings should be tied. rope_theta (`float`, *optional*, defaults to 10000.0): The base period of the RoPE embeddings. use_sliding_window (`bool`, *optional*, defaults to `False`): Whether to use sliding window attention. sliding_window (`int`, *optional*, defaults to 4096): Sliding window attention (SWA) window size. If not specified, will default to `4096`. max_window_layers (`int`, *optional*, defaults to 28): The number of layers that use SWA (Sliding Window Attention). The bottom layers use SWA while the top use full attention. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. ```python >>> from transformers import Qwen2Model, Qwen2Config >>> # Initializing a Qwen2 style configuration >>> configuration = Qwen2Config() >>> # Initializing a model from the Qwen2-7B style configuration >>> model = Qwen2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "qwen2" keys_to_ignore_at_inference = ["past_key_values"] def __init__( self, vocab_size=151936, hidden_size=4096, intermediate_size=22016, num_hidden_layers=32, num_attention_heads=32, num_key_value_heads=32, hidden_act="silu", max_position_embeddings=32768, initializer_range=0.02, rms_norm_eps=1e-6, use_cache=True, tie_word_embeddings=False, rope_theta=10000.0, use_sliding_window=False, sliding_window=4096, max_window_layers=28, attention_dropout=0.0, hyper_layers=[1,9,17,25], **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 self.use_sliding_window = use_sliding_window self.sliding_window = sliding_window if use_sliding_window else None self.max_window_layers = max_window_layers # 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.rope_theta = rope_theta self.attention_dropout = attention_dropout self.hyper_layers = hyper_layers super().__init__( tie_word_embeddings=tie_word_embeddings, **kwargs, )