image-match/python/py/Lib/site-packages/transformers/models/glm46v/configuration_glm46v.py

#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/glm46v/modular_glm46v.py.
#               Do NOT edit this file manually as any edits will be overwritten by the generation of
#             the file from the modular. If any change should be done, please apply the change to the
#                          modular_glm46v.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2025 the HuggingFace 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.


from huggingface_hub.dataclasses import strict

from ...configuration_utils import PreTrainedConfig
from ...utils import auto_docstring
from ..auto import CONFIG_MAPPING, AutoConfig


@auto_docstring(checkpoint="zai-org/GLM-4.1V-9B-Thinking")
@strict
class Glm46VConfig(PreTrainedConfig):
    r"""
    image_start_token_id (`int`, *optional*, defaults to 151339):
        The image start token index to encode the start of image.
    image_end_token_id (`int`, *optional*, defaults to 151340):
        The image end token index to encode the end of image.
    video_start_token_id (`int`, *optional*, defaults to 151361):
        The video start token index to encode the start of video.
    video_end_token_id (`int`, *optional*, defaults to 151362):
        The video end token index to encode the end of video.

    ```python
    >>> from transformers import Glm46VForConditionalGeneration, Glm46VConfig

    >>> # Initializing a GLM-4.6V style configuration
    >>> configuration = Glm46VConfig()

    >>> # Initializing a model from the GLM-4.6V style configuration
    >>> model = Glm4vForConditionalGeneration(configuration)

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

    model_type = "glm46v"
    sub_configs = {"text_config": AutoConfig, "vision_config": AutoConfig}
    keys_to_ignore_at_inference = ["past_key_values"]

    text_config: dict | PreTrainedConfig | None = None
    vision_config: dict | PreTrainedConfig | None = None
    image_token_id: int = 151343
    video_token_id: int = 151344
    image_start_token_id: int = 151339
    image_end_token_id: int = 151340
    video_start_token_id: int = 151361
    video_end_token_id: int = 151362
    tie_word_embeddings: bool = False

    def __post_init__(self, **kwargs):
        if isinstance(self.vision_config, dict):
            self.vision_config["model_type"] = self.vision_config.get("model_type", "glm4v_vision")
            self.vision_config = CONFIG_MAPPING[self.vision_config["model_type"]](**self.vision_config)
        elif self.vision_config is None:
            self.vision_config = CONFIG_MAPPING["glm4v_vision"]()

        if isinstance(self.text_config, dict):
            self.text_config["model_type"] = self.text_config.get("model_type", "glm4v_text")
            self.text_config = CONFIG_MAPPING[self.text_config["model_type"]](**self.text_config)
        elif self.text_config is None:
            self.text_config = CONFIG_MAPPING["glm4v_text"]()

        super().__post_init__(**kwargs)


__all__ = ["Glm46VConfig"]