# Copyright 2025 the Cohere 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.


from huggingface_hub.dataclasses import strict

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


@auto_docstring(checkpoint="CohereLabs/command-a-vision-07-2025")
@strict
class Cohere2VisionConfig(PreTrainedConfig):
    r"""
    downsample_factor (`int`, *optional*, defaults to 2):
        The factor by which to downsample the input image.
    alignment_intermediate_size (`int`, *optional*, defaults to 36864):
        The size of the intermediate layer for alignment.
    """

    model_type = "cohere2_vision"
    sub_configs_defaults = {
        "vision_config": SubConfigSpec(
            config_class=AutoConfig,
            model_type="siglip_vision_model",
            init_kwargs={
                "hidden_size": 1152,
                "intermediate_size": 3072,
                "image_size": 512,
                "num_hidden_layers": 27,
                "num_attention_heads": 12,
            },
        ),
        "text_config": SubConfigSpec(config_class=AutoConfig, model_type="cohere2"),
    }

    vision_config: dict | PreTrainedConfig | None = None
    text_config: dict | PreTrainedConfig | None = None
    downsample_factor: int = 2
    image_token_id: int = 255036
    alignment_intermediate_size: int = 36864
    tie_word_embeddings: bool = True


__all__ = ["Cohere2VisionConfig"]