from typing import Callable, Optional

import torch
from torch import nn

from transformers.utils.generic import check_model_inputs

from ...cache_utils import Cache, DynamicCache
from ...masking_utils import create_causal_mask, create_sliding_window_causal_mask
from ...modeling_flash_attention_utils import FlashAttentionKwargs
from ...modeling_layers import (
    GenericForQuestionAnswering,
)
from ...modeling_outputs import BaseModelOutputWithPast
from ...modeling_utils import ALL_ATTENTION_FUNCTIONS
from ...processing_utils import Unpack
from ...utils import TransformersKwargs, auto_docstring, logging
from ..llama.modeling_llama import (
    LlamaAttention,
    LlamaDecoderLayer,
    LlamaForCausalLM,
    LlamaForSequenceClassification,
    LlamaForTokenClassification,
    LlamaMLP,
    LlamaModel,
    LlamaPreTrainedModel,
    apply_rotary_pos_emb,
    eager_attention_forward,
)
from .configuration_mistral import MistralConfig


logger = logging.get_logger(__name__)


class MistralMLP(LlamaMLP):
    def __init__(self, config):
        super().__init__(config)
        self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
        self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
        self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=False)


class MistralAttention(LlamaAttention):
    def __init__(self, config: MistralConfig, layer_idx: int):
        super().__init__()
        self.head_dim = getattr(config, "head_dim", None) or config.hidden_size // config.num_attention_heads
        self.q_proj = nn.Linear(config.hidden_size, config.num_attention_heads * self.head_dim, bias=False)
        self.k_proj = nn.Linear(config.hidden_size, config.num_key_value_heads * self.head_dim, bias=False)
        self.v_proj = nn.Linear(config.hidden_size, config.num_key_value_heads * self.head_dim, bias=False)
        self.o_proj = nn.Linear(config.num_attention_heads * self.head_dim, config.hidden_size, bias=False)

    def forward(
        self,
        hidden_states: torch.Tensor,
        position_embeddings: tuple[torch.Tensor, torch.Tensor],
        attention_mask: Optional[torch.Tensor],
        past_key_value: Optional[Cache] = None,
        cache_position: Optional[torch.LongTensor] = None,
        **kwargs: Unpack[FlashAttentionKwargs],
    ) -> tuple[torch.Tensor, Optional[torch.Tensor], Optional[tuple[torch.Tensor]]]:
        input_shape = hidden_states.shape[:-1]
        hidden_shape = (*input_shape, -1, self.head_dim)

        query_states = self.q_proj(hidden_states).view(hidden_shape).transpose(1, 2)
        key_states = self.k_proj(hidden_states).view(hidden_shape).transpose(1, 2)
        value_states = self.v_proj(hidden_states).view(hidden_shape).transpose(1, 2)

        cos, sin = position_embeddings
        query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin)

        if past_key_value is not None:
            # sin and cos are specific to RoPE models; cache_position needed for the static cache
            cache_kwargs = {"sin": sin, "cos": cos, "cache_position": cache_position}
            key_states, value_states = past_key_value.update(key_states, value_states, self.layer_idx, cache_kwargs)

        attention_interface: Callable = eager_attention_forward
        if self.config._attn_implementation != "eager":
            attention_interface = ALL_ATTENTION_FUNCTIONS[self.config._attn_implementation]

        attn_output, attn_weights = attention_interface(
            self,
            query_states,
            key_states,
            value_states,
            attention_mask,
            dropout=0.0 if not self.training else self.attention_dropout,
            scaling=self.scaling,
            sliding_window=getattr(self.config, "sliding_window", None),  # main diff with Llama
            **kwargs,
        )

        attn_output = attn_output.reshape(*input_shape, -1).contiguous()
        attn_output = self.o_proj(attn_output)
        return attn_output, attn_weights


class MistralDecoderLayer(LlamaDecoderLayer):
    def __init__(self, config: MistralConfig, layer_idx: int):
        super().__init__(config, layer_idx)
        self.self_attn = MistralAttention(config=config, layer_idx=layer_idx)
        self.mlp = MistralMLP(config)


class MistralPreTrainedModel(LlamaPreTrainedModel):
    _can_record_outputs = {
        "hidden_states": MistralDecoderLayer,
        "attentions": MistralAttention,
    }


class MistralModel(LlamaModel):
    @check_model_inputs
    @auto_docstring
    def forward(
        self,
        input_ids: Optional[torch.LongTensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        past_key_values: Optional[Cache] = None,
        inputs_embeds: Optional[torch.FloatTensor] = None,
        use_cache: Optional[bool] = None,
        cache_position: Optional[torch.LongTensor] = None,
        **kwargs: Unpack[TransformersKwargs],
    ) -> BaseModelOutputWithPast:
        if (input_ids is None) ^ (inputs_embeds is not None):
            raise ValueError("You must specify exactly one of input_ids or inputs_embeds")

        if inputs_embeds is None:
            inputs_embeds = self.embed_tokens(input_ids)

        if use_cache and past_key_values is None:
            past_key_values = DynamicCache()

        if cache_position is None:
            past_seen_tokens = past_key_values.get_seq_length() if past_key_values is not None else 0
            cache_position = torch.arange(
                past_seen_tokens, past_seen_tokens + inputs_embeds.shape[1], device=inputs_embeds.device
            )

        if position_ids is None:
            position_ids = cache_position.unsqueeze(0)

        mask_function = create_causal_mask if self.config.sliding_window is None else create_sliding_window_causal_mask
        causal_mask = mask_function(
            config=self.config,
            input_embeds=inputs_embeds,
            attention_mask=attention_mask,
            cache_position=cache_position,
            past_key_values=past_key_values,
            position_ids=position_ids,
        )

        hidden_states = inputs_embeds
        position_embeddings = self.rotary_emb(hidden_states, position_ids)

        for decoder_layer in self.layers[: self.config.num_hidden_layers]:
            hidden_states = decoder_layer(
                hidden_states,
                attention_mask=causal_mask,
                position_ids=position_ids,
                past_key_value=past_key_values,
                use_cache=use_cache,
                cache_position=cache_position,
                position_embeddings=position_embeddings,
                **kwargs,
            )
        hidden_states = self.norm(hidden_states)
        return BaseModelOutputWithPast(
            last_hidden_state=hidden_states,
            past_key_values=past_key_values if use_cache else None,
        )


class MistralForCausalLM(LlamaForCausalLM):
    pass


class MistralForTokenClassification(LlamaForTokenClassification):
    pass


class MistralForSequenceClassification(LlamaForSequenceClassification):
    pass


class MistralForQuestionAnswering(GenericForQuestionAnswering, MistralPreTrainedModel): ...


__all__ = [
    "MistralForCausalLM",
    "MistralForQuestionAnswering",
    "MistralModel",
    "MistralPreTrainedModel",
    "MistralForSequenceClassification",
    "MistralForTokenClassification",
]