configuration_magma.py

# coding=utf-8
# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
#
# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
# and OPT implementations in this library. It has been modified from its
# original forms to accommodate minor architectural differences compared
# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
#
# 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.
"""Magma model configuration"""

from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
from transformers.models.auto import CONFIG_MAPPING

logger = logging.get_logger(__name__)


class MagmaConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`MagmaModel`]. It is used to instantiate an Magma
    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 Magma-7B.

    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 32000):
            Vocabulary size of the Magma model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`MagmaModel`]
        hidden_size (`int`, *optional*, defaults to 4096):
            Dimension of the hidden representations.
        intermediate_size (`int`, *optional*, defaults to 11008):
            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`.
        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 2048):
            The maximum sequence length that this model might ever be used with. Magma 1 supports up to 2048 tokens,
            Magma 2 up to 4096, CodeMagma up to 16384.
        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`.
        pad_token_id (`int`, *optional*):
            Padding token id.
        bos_token_id (`int`, *optional*, defaults to 1):
            Beginning of stream token id.
        eos_token_id (`int`, *optional*, defaults to 2):
            End of stream token id.
        pretraining_tp (`int`, *optional*, defaults to 1):
            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
            document](https://huggingface.co/docs/transformers/main/perf_train_gpu_many#tensor-parallelism) to understand more about it. This value is
            necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
            issue](https://github.com/pytorch/pytorch/issues/76232).
        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*):
            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
            `max_position_embeddings` to the expected new maximum.
        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.
        mlp_bias (`bool`, *optional*, defaults to `False`):
            Whether to use a bias in up_proj, down_proj and gate_proj layers in the MLP layers.

    ```python
    >>> from transformers import MagmaModel, MagmaConfig

    >>> # Initializing a Magma magma-7b style configuration
    >>> configuration = MagmaConfig()

    >>> # Initializing a model from the magma-7b style configuration
    >>> model = MagmaModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "magma" 
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vision_config=None,
        text_config=None,
        image_token_id=None,
        tie_word_embeddings=False,
        **kwargs,
    ):
        self.vision_config = vision_config      
        self.image_token_index = image_token_id

        if isinstance(text_config, dict):
            text_config["model_type"] = text_config["model_type"] if "model_type" in text_config else "llama"
            text_config = CONFIG_MAPPING[text_config["model_type"]](**text_config)
        elif text_config is None:
            if "model_type" in kwargs:
                text_config = CONFIG_MAPPING[kwargs["model_type"]](**kwargs)

        if text_config is not None:
            # copy all variables in text_config to self
            for key, value in text_config.__dict__.items():
                if not key.startswith("_") and not key.startswith("__"):
                    setattr(self, key, value)
            self.text_config = text_config
        else:
            self.text_config = None

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