configuration_mitsua_japanese_clip.py

# coding=utf-8
# Copyright 2024 The HuggingFace Inc. team. + Abstract Engine. 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.
from transformers import PretrainedConfig, CLIPVisionConfig, SiglipTextConfig

class MitsuaJapaneseCLIPConfig(PretrainedConfig):
    model_type = "mitsua_japanese_clip"

    def __init__(
        self,
        text_config=None, vision_config=None, 
        projection_dim=512,
        logit_scale_init_value=2.6592,
        **kwargs,
    ):
        super().__init__(**kwargs)
        if text_config is None:
            text_config = {}
        if vision_config is None:
            vision_config = {}

        self.vision_config = CLIPVisionConfig(**vision_config)
        self.text_config = SiglipTextConfig(**text_config)

        self.projection_dim = projection_dim
        self.logit_scale_init_value = logit_scale_init_value
        self.initializer_factor = 1.0


    @classmethod
    def from_vision_text_configs(
        cls, vision_config: PretrainedConfig, text_config: PretrainedConfig, **kwargs
    ):
        r"""
        Instantiate a [`VisionTextDualEncoderConfig`] (or a derived class) from text model configuration and vision
        model configuration.
        Returns:
            [`VisionTextDualEncoderConfig`]: An instance of a configuration object
        """

        return cls(
            vision_config=vision_config.to_dict(),
            text_config=text_config.to_dict(),
            **kwargs,
        )