configuration_phi.py

# coding=utf-8
# Copyright 2023 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 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.

#Phi model configuration


from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging


logger = logging.get_logger(__name__)

PHI_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "microsoft/phi-2": "https://huggingface.co/microsoft/phi-2/resolve/main/config.json",
}


class PhiConfig(PretrainedConfig):


    model_type = "phi"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vocab_size=51200,
        hidden_size=2048,
        intermediate_size=8192,
        num_hidden_layers=24,
        num_experts_per_tok=2,     ###ADDED
        num_attention_heads=32,
        num_key_value_heads=None,
        num_local_experts=2,       ###ADDED
        resid_pdrop=0.0,
        embd_pdrop=0.0,
        attention_dropout=0.0,
        hidden_act="gelu_new",
        max_position_embeddings=2048,
        initializer_range=0.02,
        layer_norm_eps=1e-5,
        use_cache=True,
        tie_word_embeddings=False,
        rope_theta=10000.0,
        rope_scaling=None,
        partial_rotary_factor=0.5,
        qk_layernorm=False,
        bos_token_id=1,
        eos_token_id=2,
        **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_experts_per_tok = num_experts_per_tok   ###ADDED
        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.num_local_experts = num_local_experts       ###ADDED
        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.initializer_range = initializer_range
        self.layer_norm_eps = layer_norm_eps
        self.use_cache = use_cache
        self.rope_theta = rope_theta
        self.rope_scaling = rope_scaling
        self.partial_rotary_factor = partial_rotary_factor
        self.qk_layernorm = qk_layernorm
        self._rope_scaling_validation()

        super().__init__(
            bos_token_id=bos_token_id,
            eos_token_id=eos_token_id,
            tie_word_embeddings=tie_word_embeddings,
            **kwargs,
        )

    # Copied from transformers.models.llama.configuration_llama.LlamaConfig._rope_scaling_validation
    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) != 2:
            raise ValueError(
                "`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, "
                f"got {self.rope_scaling}"
            )
        rope_scaling_type = self.rope_scaling.get("type", None)
        rope_scaling_factor = self.rope_scaling.get("factor", None)
        if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]:
            raise ValueError(
                f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
            )
        if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor <= 1.0:
            raise ValueError(f"`rope_scaling`'s factor field must be a float > 1, got {rope_scaling_factor}")