# Copyright 2024 Cohere 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.
"""Cohere model configuration"""

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="CohereForAI/c4ai-command-r-v01")
@strict
class CohereConfig(PreTrainedConfig):
    r"""
    logit_scale (`float`, *optional*, defaults to 0.0625):
        The scaling factor for the output logits.

    ```python
    >>> from transformers import CohereModel, CohereConfig

    >>> # Initializing a Cohere model configuration
    >>> configuration = CohereConfig()

    >>> # Initializing a model from the Cohere configuration
    >>> model = CohereModel(configuration) # doctest: +SKIP

    >>> # Accessing the model configuration
    >>> configuration = model.config # doctest: +SKIP
    ```
    """

    model_type = "cohere"
    keys_to_ignore_at_inference = ["past_key_values"]
    default_theta = 500000.0
    base_model_tp_plan = {
        "layers.*.self_attn.q_proj": "colwise",
        "layers.*.self_attn.k_proj": "colwise",
        "layers.*.self_attn.v_proj": "colwise",
        "layers.*.self_attn.o_proj": "rowwise",
        "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 = 256000
    hidden_size: int = 8192
    intermediate_size: int = 22528
    logit_scale: float | None = 0.0625
    num_hidden_layers: int = 40
    num_attention_heads: int = 64
    num_key_value_heads: int | None = None
    hidden_act: str = "silu"
    max_position_embeddings: int = 8192
    initializer_range: float = 0.02
    layer_norm_eps: float | None = 1e-5
    use_cache: bool = True
    pad_token_id: int | None = 0
    bos_token_id: int | None = 5
    eos_token_id: int | list[int] | None = 255001
    tie_word_embeddings: bool = True
    rope_parameters: RopeParameters | dict | None = None
    attention_bias: bool = False
    attention_dropout: float | int | None = 0.0
    use_qk_norm: bool | None = False

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

        super().__post_init__(**kwargs)


__all__ = ["CohereConfig"]