# coding=utf-8
# 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 typing import Optional

import torch

from ...cache_utils import Cache
from ..gemma2.configuration_gemma2 import Gemma2Config
from ..gemma2.modeling_gemma2 import Gemma2DecoderLayer, Gemma2ForCausalLM


class VaultGemmaConfig(Gemma2Config):
    pass


class VaultGemmaDecoderLayer(Gemma2DecoderLayer):
    def __init__(self, **super_kwargs):
        super().__init__(**super_kwargs)
        del self.post_attention_layernorm
        del self.post_feedforward_layernorm

    def forward(
        self,
        hidden_states: torch.Tensor,
        position_embeddings: tuple[torch.Tensor, torch.Tensor],
        attention_mask: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        past_key_values: Optional[Cache] = None,
        output_attentions: Optional[bool] = False,
        use_cache: Optional[bool] = False,
        cache_position: Optional[torch.LongTensor] = None,
        **kwargs,
    ) -> tuple[torch.FloatTensor, Optional[tuple[torch.FloatTensor, torch.FloatTensor]]]:
        residual = hidden_states
        hidden_states = self.input_layernorm(hidden_states)
        # Self Attention
        hidden_states, self_attn_weights = self.self_attn(
            hidden_states=hidden_states,
            position_embeddings=position_embeddings,
            attention_mask=attention_mask,
            position_ids=position_ids,
            past_key_values=past_key_values,
            output_attentions=output_attentions,
            use_cache=use_cache,
            cache_position=cache_position,
            **kwargs,
        )
        hidden_states = residual + hidden_states

        residual = hidden_states
        hidden_states = self.pre_feedforward_layernorm(hidden_states)
        hidden_states = self.mlp(hidden_states)
        hidden_states = residual + hidden_states

        outputs = (hidden_states,)
        if output_attentions:
            outputs += (self_attn_weights,)

        return outputs


class VaultGemmaForCausalLM(Gemma2ForCausalLM):
    pass


__all__ = [
    "VaultGemmaConfig",
    "VaultGemmaForCausalLM",
    "VaultGemmaModel",  # noqa: F822
    "VaultGemmaPreTrainedModel",  # noqa: F822
]