# Copyright 2024 Microsoft 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 atd # # 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. """ Phi-3 model configuration""" from transformers.configuration_utils import PretrainedConfig from transformers.utils import logging logger = logging.get_logger(__name__) PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = { 'microsoft/Phi-3-mini-4k-instruct': 'https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json', 'microsoft/Phi-3-mini-128k-instruct': 'https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json', } class Phi3Config(PretrainedConfig): r""" This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3 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 [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct). 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 32064): Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Phi3Model`]. hidden_size (`int`, *optional*, defaults to 3072): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 8192): 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 checkout [this paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `num_attention_heads`. resid_pdrop (`float`, *optional*, defaults to 0.0): Dropout probability for mlp outputs. embd_pdrop (`int`, *optional*, defaults to 0.0): The dropout ratio for the embeddings. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio after computing the attention scores. 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. original_max_position_embeddings (`int`, *optional*, defaults to 4096): The maximum sequence length that this model was trained with. This is used to determine the size of the original RoPE embeddings when using long scaling. 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 value used for the RMSNorm. 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`. Whether to tie weight embeddings or not. 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*): The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be either `su` or `yarn` and the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size divided by the number of attention heads divided by 2. bos_token_id (`int`, *optional*, defaults to 1): The id of the "beginning-of-sequence" token. eos_token_id (`int`, *optional*, defaults to 32000): The id of the "end-of-sequence" token. pad_token_id (`int`, *optional*, defaults to 32000): The id of the padding token. sliding_window (`int`, *optional*): Sliding window attention window size. If `None`, no sliding window is applied. Example: ```python >>> from transformers import Phi3Model, Phi3Config >>> # Initializing a Phi-3 style configuration >>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct") >>> # Initializing a model from the configuration >>> model = Phi3Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = 'phi3' keys_to_ignore_at_inference = ['past_key_values'] def __init__( self, vocab_size=32064, hidden_size=3072, intermediate_size=8192, num_hidden_layers=32, num_attention_heads=32, num_key_value_heads=None, resid_pdrop=0.0, embd_pdrop=0.0, attention_dropout=0.0, hidden_act='silu', max_position_embeddings=4096, original_max_position_embeddings=4096, initializer_range=0.02, rms_norm_eps=1e-5, use_cache=True, tie_word_embeddings=False, rope_theta=10000.0, rope_scaling=None, bos_token_id=1, eos_token_id=32000, pad_token_id=32000, sliding_window=None, **kwargs, ): self.vocab_size = vocab_size self.hidden_size = hidden_size self.intermediate_size = intermediate_size self.num_hidden_layers = num_hidden_layers self.num_attention_heads = num_attention_heads if num_key_value_heads is None: num_key_value_heads = num_attention_heads self.num_key_value_heads = num_key_value_heads self.resid_pdrop = resid_pdrop self.embd_pdrop = embd_pdrop self.attention_dropout = attention_dropout self.hidden_act = hidden_act self.max_position_embeddings = max_position_embeddings self.original_max_position_embeddings = original_max_position_embeddings self.initializer_range = initializer_range self.rms_norm_eps = rms_norm_eps self.use_cache = use_cache self.rope_theta = rope_theta self.rope_scaling = rope_scaling self._rope_scaling_validation() self.sliding_window = sliding_window super().__init__( bos_token_id=bos_token_id, eos_token_id=eos_token_id, pad_token_id=pad_token_id, tie_word_embeddings=tie_word_embeddings, **kwargs, ) def _rope_scaling_validation(self): """ Validate the `rope_scaling` configuration. """ if self.rope_scaling is None: return if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3: raise ValueError( '`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, ' f'got {self.rope_scaling}' ) rope_scaling_type = self.rope_scaling.get('type', None) rope_scaling_short_factor = self.rope_scaling.get('short_factor', None) rope_scaling_long_factor = self.rope_scaling.get('long_factor', None) if rope_scaling_type is None or rope_scaling_type not in ['su', 'yarn']: raise ValueError(f"`rope_scaling`'s type field must be one of ['su', 'yarn'], got {rope_scaling_type}") if not ( isinstance(rope_scaling_short_factor, list) and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor) ): raise ValueError( f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}" ) if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2: raise ValueError( f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}" ) if not ( isinstance(rope_scaling_long_factor, list) and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor) ): raise ValueError( f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}" ) if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2: raise ValueError( f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}" )