#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/olmo3/modular_olmo3.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_olmo3.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 ...modeling_rope_utils import RopeParameters
from ...utils import auto_docstring


@auto_docstring(checkpoint="allenai/Olmo-3-7B-Instruct")
@strict
class Olmo3Config(PreTrainedConfig):
    r"""
    Example:

    ```python
    >>> from transformers import Olmo3Model, Olmo3Config

    >>> # Initializing a Olmo3 7B style configuration
    >>> configuration = Olmo3Config()

    >>> # Initializing a model from the Olmo3 7B style configuration
    >>> model = Olmo3Model(configuration)

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

    model_type = "olmo3"
    keys_to_ignore_at_inference = ["past_key_values"]
    base_model_tp_plan = {
        "layers.*.self_attn.q_proj": "colwise_gather_output",  # we need to replicate here due to the added norm on q and k
        "layers.*.self_attn.k_proj": "colwise_gather_output",  # we need to replicate here due to the added norm on q and k
        "layers.*.self_attn.v_proj": "colwise_gather_output",  # we need to replicate here due to the added norm on q and k
        "layers.*.self_attn.o_proj": "rowwise_split_input",  # input is replicated due to the added norm on q and k
        "layers.*.mlp.gate_proj": "colwise",
        "layers.*.mlp.up_proj": "colwise",
        "layers.*.mlp.down_proj": "rowwise",
    }
    base_model_pp_plan = {
        "embed_tokens": (["input_ids"], ["inputs_embeds"]),
        "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
        "norm": (["hidden_states"], ["hidden_states"]),
    }

    vocab_size: int = 50304
    hidden_size: int = 4096
    intermediate_size: int = 11008
    num_hidden_layers: int = 32
    num_attention_heads: int = 32
    num_key_value_heads: int | None = None
    hidden_act: str = "silu"
    max_position_embeddings: int = 2048
    initializer_range: float = 0.02
    use_cache: bool = True
    pad_token_id: int | None = 1
    bos_token_id: int | None = None
    eos_token_id: int | list[int] | None = 50279
    tie_word_embeddings: bool = False
    rope_parameters: RopeParameters | dict | None = None
    attention_bias: bool = False
    attention_dropout: float | int = 0.0

    rms_norm_eps: float = 1e-5

    sliding_window: int | None = 4096
    layer_types: list[str] | None = None

    def __post_init__(self, **kwargs):
        if self.num_key_value_heads is None:
            self.num_key_value_heads = self.num_attention_heads

        if self.layer_types is None:
            self.layer_types = [
                "sliding_attention" if (i + 1) % 4 != 0 else "full_attention" for i in range(self.num_hidden_layers)
            ]
        if self.num_key_value_heads is None:
            self.num_key_value_heads = self.num_attention_heads
        super().__post_init__(**kwargs)


__all__ = ["Olmo3Config"]