# coding=utf-8 # Copyright 2025 The BitNet Team and The HuggingFace Inc. team. All rights reserved. # # 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 """BitNet model configuration""" from ...configuration_utils import PretrainedConfig from ...utils import logging logger = logging.get_logger(__name__) class BitNetConfig(PretrainedConfig): r""" This is the configuration class to store the configuration of a [`BitNetModel`]. It is used to instantiate an BitNet model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of BitNet b1.58 2B4T [microsoft/bitnet-b1.58-2B-4T](https://huggingface.co/microsoft/bitnet-b1.58-2B-4T). 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 128256): Vocabulary size of the BitNet model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`BitNetModel`] hidden_size (`int`, *optional*, defaults to 2560): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 6912): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 30): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 20): Number of attention heads for each attention layer in the Transformer decoder. num_key_value_heads (`int`, *optional*, defaults to 5): 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 `"relu2"`): 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. 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*): Padding token id. bos_token_id (`int`, *optional*, defaults to 128000): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 128001): End of stream token id. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings rope_theta (`float`, *optional*, defaults to 500000.0): The base period of the RoPE embeddings. attention_bias (`bool`, *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. ```python >>> from transformers import BitNetModel, BitNetConfig >>> # Initializing a BitNet style configuration >>> configuration = BitNetConfig() >>> # Initializing a model from the BitNet style configuration >>> model = BitNetModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "bitnet" keys_to_ignore_at_inference = ["past_key_values"] def __init__( self, vocab_size=128256, hidden_size=2560, intermediate_size=6912, num_hidden_layers=30, num_attention_heads=20, num_key_value_heads=5, hidden_act="relu2", max_position_embeddings=2048, initializer_range=0.02, rms_norm_eps=1e-5, use_cache=True, pad_token_id=None, bos_token_id=128000, eos_token_id=128001, tie_word_embeddings=False, rope_theta=500000.0, attention_bias=False, attention_dropout=0.0, **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.rope_theta = rope_theta self.attention_bias = attention_bias self.attention_dropout = attention_dropout super().__init__( pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, tie_word_embeddings=tie_word_embeddings, **kwargs, ) __all__ = ["BitNetConfig"]