# coding=utf-8
# Copyright (C) 2025 THL A29 Limited, a Tencent company and the HuggingFace 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.
"""PyTorch HunYuanDenseV1 model."""

from typing import Callable, Optional

import torch
from torch import nn

from transformers.cache_utils import Cache
from transformers.utils import (
    logging,
)

from ...modeling_rope_utils import ROPE_INIT_FUNCTIONS, dynamic_rope_update
from ...modeling_utils import ALL_ATTENTION_FUNCTIONS
from ...processing_utils import Unpack
from ...utils import TransformersKwargs
from ..llama.modeling_llama import (
    LlamaAttention,
    LlamaDecoderLayer,
    LlamaForCausalLM,
    LlamaForSequenceClassification,
    LlamaMLP,
    LlamaModel,
    LlamaPreTrainedModel,
    LlamaRMSNorm,
    apply_rotary_pos_emb,
    eager_attention_forward,
)
from .configuration_hunyuan_v1_dense import HunYuanDenseV1Config


logger = logging.get_logger(__name__)


class HunYuanDenseV1RMSNorm(LlamaRMSNorm):
    pass


class HunYuanDenseV1MLP(LlamaMLP):
    def __init__(self, config: HunYuanDenseV1Config, layer_idx=None, is_shared_mlp=False):
        super().__init__(config)
        self.layer_idx = layer_idx
        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 HunYuanDenseV1Attention(LlamaAttention):
    def __init__(self, config: HunYuanDenseV1Config, layer_idx: int):
        super().__init__(config, layer_idx)
        self.query_layernorm = HunYuanDenseV1RMSNorm(self.head_dim, eps=config.rms_norm_eps)
        self.key_layernorm = HunYuanDenseV1RMSNorm(self.head_dim, eps=config.rms_norm_eps)

    def forward(
        self,
        hidden_states: torch.Tensor,
        position_embeddings: tuple[torch.Tensor, torch.Tensor],
        attention_mask: Optional[torch.Tensor],
        past_key_values: Optional[Cache] = None,
        cache_position: Optional[torch.LongTensor] = None,
        **kwargs: Unpack[TransformersKwargs],
    ) -> tuple[torch.Tensor, 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)
        query_states = self.query_layernorm(query_states)
        key_states = self.key_layernorm(key_states)

        if past_key_values 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_values.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,
            **kwargs,
        )

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


class HunYuanDenseV1DecoderLayer(LlamaDecoderLayer):
    def __init__(self, config: HunYuanDenseV1Config, layer_idx: int):
        super().__init__(config, layer_idx)
        self.layer_idx = layer_idx


class HunYuanDenseV1PreTrainedModel(LlamaPreTrainedModel):
    def _init_weights(self, module):
        std = self.config.initializer_range
        if isinstance(module, nn.Linear):
            module.weight.data.normal_(mean=0.0, std=std)
            if module.bias is not None:
                module.bias.data.zero_()
        elif isinstance(module, nn.Embedding):
            module.weight.data.normal_(mean=0.0, std=std)
            if module.padding_idx is not None:
                module.weight.data[module.padding_idx].zero_()


class HunYuanDenseV1RotaryEmbedding(nn.Module):
    inv_freq: torch.Tensor  # fix linting for `register_buffer`

    def __init__(self, config: HunYuanDenseV1Config, device=None):
        super().__init__()
        # BC: "rope_type" was originally "type"
        if hasattr(config, "rope_scaling") and isinstance(config.rope_scaling, dict):
            self.rope_type = config.rope_scaling.get("rope_type", config.rope_scaling.get("type"))
        else:
            self.rope_type = "default"
        self.max_seq_len_cached = config.max_position_embeddings
        self.original_max_seq_len = config.max_position_embeddings

        self.config = config
        self.rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type]
        if self.rope_type == "dynamic" and config.rope_scaling["alpha"]:
            # DynamicNTKAlphaRotary
            self.dim = config.head_dim
            base = config.rope_theta * config.rope_scaling.get("alpha") ** (self.dim / (self.dim - 2))
            inv_freq = 1.0 / (base ** (torch.arange(0, self.dim, 2).float().to(device) / self.dim))
            self.attention_scaling = 1.0
        else:
            inv_freq, self.attention_scaling = self.rope_init_fn(self.config, device)

        self.register_buffer("inv_freq", inv_freq, persistent=False)
        self.original_inv_freq = self.inv_freq

    @torch.no_grad()
    @dynamic_rope_update  # power user: used with advanced RoPE types (e.g. dynamic rope)
    def forward(self, x, position_ids):
        inv_freq_expanded = self.inv_freq[None, :, None].float().expand(position_ids.shape[0], -1, 1).to(x.device)
        position_ids_expanded = position_ids[:, None, :].float()

        device_type = x.device.type if isinstance(x.device.type, str) and x.device.type != "mps" else "cpu"
        with torch.autocast(device_type=device_type, enabled=False):  # Force float32
            freqs = (inv_freq_expanded.float() @ position_ids_expanded.float()).transpose(1, 2)
            emb = torch.cat((freqs, freqs), dim=-1)
            cos = emb.cos() * self.attention_scaling
            sin = emb.sin() * self.attention_scaling

        return cos.to(dtype=x.dtype), sin.to(dtype=x.dtype)


class HunYuanDenseV1Model(LlamaModel):
    pass


class HunYuanDenseV1ForCausalLM(LlamaForCausalLM):
    pass


class HunYuanDenseV1ForSequenceClassification(LlamaForSequenceClassification):
    pass


__all__ = [
    "HunYuanDenseV1ForCausalLM",
    "HunYuanDenseV1Model",
    "HunYuanDenseV1PreTrainedModel",
    "HunYuanDenseV1ForSequenceClassification",
]