Noumaan/pythonGPT-Sharded

1# coding=utf-82# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.3#4# Licensed under the Apache License, Version 2.0 (the "License");5# you may not use this file except in compliance with the License.6# You may obtain a copy of the License at7#8#     http://www.apache.org/licenses/LICENSE-2.09#10# Unless required by applicable law or agreed to in writing, software11# distributed under the License is distributed on an "AS IS" BASIS,12# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.13# See the License for the specific language governing permissions and14# limitations under the License.15 16""" Phi-3 model configuration"""17 18 19from transformers.configuration_utils import PretrainedConfig20from transformers.utils import logging21 22 23logger = logging.get_logger(__name__)24 25PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {26    "microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",27    "microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",28}29 30 31class Phi3Config(PretrainedConfig):32    r"""33    This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-334    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the35    defaults will yield a similar configuration to that of the36    [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).37 38    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the39    documentation from [`PretrainedConfig`] for more information.40 41    Args:42        vocab_size (`int`, *optional*, defaults to 32064):43            Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the44            `inputs_ids` passed when calling [`Phi3Model`].45        hidden_size (`int`, *optional*, defaults to 3072):46            Dimension of the hidden representations.47        intermediate_size (`int`, *optional*, defaults to 8192):48            Dimension of the MLP representations.49        num_hidden_layers (`int`, *optional*, defaults to 32):50            Number of hidden layers in the Transformer decoder.51        num_attention_heads (`int`, *optional*, defaults to 32):52            Number of attention heads for each attention layer in the Transformer decoder.53        num_key_value_heads (`int`, *optional*):54            This is the number of key_value heads that should be used to implement Grouped Query Attention. If55            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if56            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When57            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed58            by meanpooling all the original heads within that group. For more details checkout [this59            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to60            `num_attention_heads`.61        resid_pdrop (`float`, *optional*, defaults to 0.0):62            Dropout probability for mlp outputs.63        embd_pdrop (`int`, *optional*, defaults to 0.0):64            The dropout ratio for the embeddings.65        attention_dropout (`float`, *optional*, defaults to 0.0):66            The dropout ratio after computing the attention scores.67        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):68            The non-linear activation function (function or string) in the decoder.69        max_position_embeddings (`int`, *optional*, defaults to 4096):70            The maximum sequence length that this model might ever be used with.71        original_max_position_embeddings (`int`, *optional*, defaults to 4096):72            The maximum sequence length that this model was trained with. This is used to determine the size of the73            original RoPE embeddings when using long scaling.74        initializer_range (`float`, *optional*, defaults to 0.02):75            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.76        rms_norm_eps (`float`, *optional*, defaults to 1e-05):77            The epsilon value used for the RMSNorm.78        use_cache (`bool`, *optional*, defaults to `True`):79            Whether or not the model should return the last key/values attentions (not used by all models). Only80            relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.81        tie_word_embeddings (`bool`, *optional*, defaults to `False`):82            Whether to tie weight embeddings83        rope_theta (`float`, *optional*, defaults to 10000.0):84            The base period of the RoPE embeddings.85        rope_scaling (`dict`, *optional*):86            The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must87            contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be either `su` or `yarn` and88            the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size89            divided by the number of attention heads divided by 2.90        bos_token_id (`int`, *optional*, defaults to 1):91            The id of the "beginning-of-sequence" token.92        eos_token_id (`int`, *optional*, defaults to 32000):93            The id of the "end-of-sequence" token.94        pad_token_id (`int`, *optional*, defaults to 32000):95            The id of the padding token.96        sliding_window (`int`, *optional*):97            Sliding window attention window size. If `None`, no sliding window is applied.98 99    Example:100 101    ```python102    >>> from transformers import Phi3Model, Phi3Config103 104    >>> # Initializing a Phi-3 style configuration105    >>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")106 107    >>> # Initializing a model from the configuration108    >>> model = Phi3Model(configuration)109 110    >>> # Accessing the model configuration111    >>> configuration = model.config112    ```"""113 114    model_type = "phi3"115    keys_to_ignore_at_inference = ["past_key_values"]116 117    def __init__(118        self,119        vocab_size=32064,120        hidden_size=3072,121        intermediate_size=8192,122        num_hidden_layers=32,123        num_attention_heads=32,124        num_key_value_heads=None,125        resid_pdrop=0.0,126        embd_pdrop=0.0,127        attention_dropout=0.0,128        hidden_act="silu",129        max_position_embeddings=4096,130        original_max_position_embeddings=4096,131        initializer_range=0.02,132        rms_norm_eps=1e-5,133        use_cache=True,134        tie_word_embeddings=False,135        rope_theta=10000.0,136        rope_scaling=None,137        bos_token_id=1,138        eos_token_id=32000,139        pad_token_id=32000,140        sliding_window=None,141        **kwargs,142    ):143        self.vocab_size = vocab_size144        self.hidden_size = hidden_size145        self.intermediate_size = intermediate_size146        self.num_hidden_layers = num_hidden_layers147        self.num_attention_heads = num_attention_heads148 149        if num_key_value_heads is None:150            num_key_value_heads = num_attention_heads151 152        self.num_key_value_heads = num_key_value_heads153        self.resid_pdrop = resid_pdrop154        self.embd_pdrop = embd_pdrop155        self.attention_dropout = attention_dropout156        self.hidden_act = hidden_act157        self.max_position_embeddings = max_position_embeddings158        self.original_max_position_embeddings = original_max_position_embeddings159        self.initializer_range = initializer_range160        self.rms_norm_eps = rms_norm_eps161        self.use_cache = use_cache162        self.rope_theta = rope_theta163        self.rope_scaling = rope_scaling164        self._rope_scaling_validation()165        self.sliding_window = sliding_window166 167        super().__init__(168            bos_token_id=bos_token_id,169            eos_token_id=eos_token_id,170            pad_token_id=pad_token_id,171            tie_word_embeddings=tie_word_embeddings,172            **kwargs,173        )174 175    def _rope_scaling_validation(self):176        """177        Validate the `rope_scaling` configuration.178        """179        if self.rope_scaling is None:180            return181 182        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:183            raise ValueError(184                "`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "185                f"got {self.rope_scaling}"186            )187        rope_scaling_type = self.rope_scaling.get("type", None)188        rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)189        rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)190        if rope_scaling_type is None or rope_scaling_type not in ["su", "yarn"]:191            raise ValueError(f"`rope_scaling`'s type field must be one of ['su', 'yarn'], got {rope_scaling_type}")192        if not (193            isinstance(rope_scaling_short_factor, list)194            and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)195        ):196            raise ValueError(197                f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"198            )199        if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2:200            raise ValueError(201                f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}"202            )203        if not (204            isinstance(rope_scaling_long_factor, list)205            and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)206        ):207            raise ValueError(208                f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"209            )210        if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2:211            raise ValueError(212                f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}"213            )214