#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/deepseek_v2/modular_deepseek_v2.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_deepseek_v2.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# coding=utf-8
# Copyright 2025 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.

import warnings
from typing import Callable, Optional, Union

import torch
import torch.nn.functional as F
from torch import nn

from ...activations import ACT2FN
from ...cache_utils import Cache, DynamicCache
from ...generation import GenerationMixin
from ...integrations import use_kernel_forward_from_hub
from ...masking_utils import create_causal_mask
from ...modeling_layers import GenericForSequenceClassification, GradientCheckpointingLayer
from ...modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast
from ...modeling_rope_utils import ROPE_INIT_FUNCTIONS, dynamic_rope_update
from ...modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel
from ...processing_utils import Unpack
from ...utils import TransformersKwargs, auto_docstring, can_return_tuple
from ...utils.deprecation import deprecate_kwarg
from ...utils.generic import check_model_inputs
from .configuration_deepseek_v2 import DeepseekV2Config


class DeepseekV2MoEGate(nn.Module):
    def __init__(self, config: DeepseekV2Config):
        super().__init__()
        self.config = config
        self.top_k = config.num_experts_per_tok
        self.num_experts = config.n_routed_experts
        self.routed_scaling_factor = config.routed_scaling_factor
        self.alpha = config.aux_loss_alpha
        self.seq_aux = config.seq_aux
        self.topk_method = config.topk_method
        self.num_group = config.n_group
        self.topk_group = config.topk_group

        # topk selection algorithm
        self.norm_topk_prob = config.norm_topk_prob
        self.gating_dim = config.hidden_size
        self.weight = nn.Parameter(torch.empty((self.num_experts, self.gating_dim)))

    def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
        batch_size, seq_len, hidden_dim = hidden_states.shape
        ### compute gating score
        hidden_states = hidden_states.view(-1, hidden_dim)
        logits = F.linear(hidden_states.type(torch.float32), self.weight.type(torch.float32), None)
        scores = logits.softmax(dim=-1, dtype=torch.float32)

        # select top-k experts
        # greedy method is used for DeepSeek-V2-Lite
        # group_limited_greedy for DeepSeek-V2 and DeepSeek-V2-Chat
        if self.topk_method == "greedy":
            topk_weight, topk_idx = torch.topk(scores, k=self.top_k, dim=-1, sorted=False)
        elif self.topk_method == "group_limited_greedy":
            group_scores = scores.view(batch_size * seq_len, self.num_group, -1).max(dim=-1).values  # [n, num_group]
            group_idx = torch.topk(group_scores, k=self.topk_group, dim=-1, sorted=False)[1]  # [n, top_k_group]
            group_mask = torch.zeros_like(group_scores)  # [n, num_group]
            group_mask.scatter_(1, group_idx, 1)  # [n, num_group]
            score_mask = (
                group_mask.unsqueeze(-1)
                .expand(batch_size * seq_len, self.num_group, self.num_experts // self.num_group)
                .reshape(batch_size * seq_len, -1)
            )  # [n, e]
            tmp_scores = scores.masked_fill(~score_mask.bool(), 0.0)  # [n, e]
            topk_weight, topk_idx = torch.topk(tmp_scores, k=self.top_k, dim=-1, sorted=False)

        topk_weight = topk_weight * self.routed_scaling_factor
        ### expert-level computation auxiliary loss
        return topk_idx, topk_weight


class DeepseekV2MoE(nn.Module):
    """
    A mixed expert module containing shared experts.
    """

    def __init__(self, config: DeepseekV2Config):
        super().__init__()
        self.config = config
        self.num_experts_per_tok = config.num_experts_per_tok

        self.experts = nn.ModuleList(
            [
                (DeepseekV2MLP(config, intermediate_size=config.moe_intermediate_size))
                for _ in range(config.n_routed_experts)
            ]
        )
        self.gate = DeepseekV2MoEGate(config)
        if config.n_shared_experts is not None:
            intermediate_size = config.moe_intermediate_size * config.n_shared_experts
            self.shared_experts = DeepseekV2MLP(config=config, intermediate_size=intermediate_size)
        self.ep_rank = 0
        self.experts_per_rank = config.n_routed_experts

    def moe(self, hidden_states: torch.Tensor, topk_ids: torch.Tensor, topk_weight: torch.Tensor) -> torch.Tensor:
        cnts = topk_ids.new_zeros((topk_ids.shape[0], len(self.experts)))
        cnts.scatter_(1, topk_ids, 1)
        tokens_per_expert = cnts.sum(dim=0)
        indices = topk_ids.view(-1).argsort()
        sorted_tokens = hidden_states[indices // topk_ids.shape[1]]

        # Process experts
        outputs = []
        start_idx = 0
        for i, num_tokens in enumerate(tokens_per_expert):
            if num_tokens == 0:
                continue
            end_idx = start_idx + num_tokens
            expert = self.experts[i + self.ep_rank * self.experts_per_rank]
            tokens_for_this_expert = sorted_tokens[start_idx:end_idx]
            expert_out = expert(tokens_for_this_expert)
            outputs.append(expert_out)
            start_idx = end_idx

        outs = torch.cat(outputs, dim=0) if outputs else sorted_tokens.new_empty(0)

        # Reorder and combine outputs
        new_x = torch.empty_like(outs)
        new_x[indices] = outs
        hidden_states = (
            new_x.view(*topk_ids.shape, -1)
            .type(topk_weight.dtype)
            .mul_(topk_weight.unsqueeze(dim=-1))
            .sum(dim=1)
            .type(new_x.dtype)
        )
        return hidden_states

    def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
        residuals = hidden_states
        orig_shape = hidden_states.shape
        topk_indices, topk_weights = self.gate(hidden_states)
        hidden_states = hidden_states.view(-1, hidden_states.shape[-1])
        hidden_states = self.moe(hidden_states, topk_indices, topk_weights).view(*orig_shape)
        hidden_states = hidden_states + self.shared_experts(residuals)
        return hidden_states


class DeepseekV2MLP(nn.Module):
    def __init__(self, config: DeepseekV2Config, hidden_size=None, intermediate_size=None):
        super().__init__()
        self.config = config
        self.hidden_size = config.hidden_size if hidden_size is None else hidden_size
        self.intermediate_size = config.intermediate_size if intermediate_size is None else intermediate_size
        self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=config.mlp_bias)
        self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=config.mlp_bias)
        self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=config.mlp_bias)
        self.act_fn = ACT2FN[config.hidden_act]

    def forward(self, x):
        down_proj = self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))
        return down_proj


@use_kernel_forward_from_hub("RMSNorm")
class DeepseekV2RMSNorm(nn.Module):
    def __init__(self, hidden_size, eps=1e-6):
        """
        DeepseekV2RMSNorm is equivalent to T5LayerNorm
        """
        super().__init__()
        self.weight = nn.Parameter(torch.ones(hidden_size))
        self.variance_epsilon = eps

    def forward(self, hidden_states):
        input_dtype = hidden_states.dtype
        hidden_states = hidden_states.to(torch.float32)
        variance = hidden_states.pow(2).mean(-1, keepdim=True)
        hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)
        return self.weight * hidden_states.to(input_dtype)

    def extra_repr(self):
        return f"{tuple(self.weight.shape)}, eps={self.variance_epsilon}"


class DeepseekV2RotaryEmbedding(nn.Module):
    inv_freq: torch.Tensor  # fix linting for `register_buffer`

    def __init__(self, config: DeepseekV2Config, device=None):
        super().__init__()
        # BC: "rope_type" was originally "type"
        self.rope_type = (
            config.rope_scaling.get("rope_type", config.rope_scaling.get("type"))
            if config.rope_scaling is not None
            else "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]

        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)
        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.to(x.device) @ position_ids_expanded).transpose(1, 2)
            freqs_cis = torch.polar(torch.ones_like(freqs), freqs)  # Convert to complex representation
            freqs_cis = freqs_cis * self.attention_scaling

        return freqs_cis


def repeat_kv(hidden_states: torch.Tensor, n_rep: int) -> torch.Tensor:
    """
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    """
    batch, num_key_value_heads, slen, head_dim = hidden_states.shape
    if n_rep == 1:
        return hidden_states
    hidden_states = hidden_states[:, :, None, :, :].expand(batch, num_key_value_heads, n_rep, slen, head_dim)
    return hidden_states.reshape(batch, num_key_value_heads * n_rep, slen, head_dim)


def eager_attention_forward(
    module: nn.Module,
    query: torch.Tensor,
    key: torch.Tensor,
    value: torch.Tensor,
    attention_mask: Optional[torch.Tensor],
    scaling: float,
    dropout: float = 0.0,
    **kwargs: Unpack[TransformersKwargs],
):
    key_states = repeat_kv(key, module.num_key_value_groups)
    value_states = repeat_kv(value, module.num_key_value_groups)

    attn_weights = torch.matmul(query, key_states.transpose(2, 3)) * scaling
    if attention_mask is not None:
        causal_mask = attention_mask[:, :, :, : key_states.shape[-2]]
        attn_weights = attn_weights + causal_mask

    attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query.dtype)
    attn_weights = nn.functional.dropout(attn_weights, p=dropout, training=module.training)
    attn_output = torch.matmul(attn_weights, value_states)
    attn_output = attn_output.transpose(1, 2).contiguous()

    return attn_output, attn_weights


def apply_rotary_emb(
    xq: torch.Tensor,
    xk: torch.Tensor,
    freqs_cis: torch.Tensor,
) -> tuple[torch.Tensor, torch.Tensor]:
    xq_ = torch.view_as_complex(xq.float().reshape(*xq.shape[:-1], -1, 2))
    xk_ = torch.view_as_complex(xk.float().reshape(*xk.shape[:-1], -1, 2))

    # Broadcast to [1, 1, seq_len, dim // 2]
    freqs_cis = freqs_cis.unsqueeze(1).to(xq_.device)

    xq_out = torch.view_as_real(xq_ * freqs_cis).flatten(3).type_as(xq)
    xk_out = torch.view_as_real(xk_ * freqs_cis).flatten(3).type_as(xk)
    return xq_out, xk_out


class DeepseekV2Attention(nn.Module):
    """Multi-headed attention from 'Attention Is All You Need' paper"""

    def __init__(self, config: DeepseekV2Config, layer_idx: Optional[int] = None):
        super().__init__()
        self.config = config
        self.layer_idx = layer_idx
        self.attention_dropout = config.attention_dropout
        self.hidden_size = config.hidden_size
        self.num_heads = config.num_attention_heads
        self.head_dim = config.head_dim
        self.max_position_embeddings = config.max_position_embeddings
        self.rope_theta = config.rope_theta
        self.q_lora_rank = config.q_lora_rank
        self.qk_rope_head_dim = config.qk_rope_head_dim
        self.kv_lora_rank = config.kv_lora_rank
        self.v_head_dim = config.v_head_dim
        self.qk_nope_head_dim = config.qk_nope_head_dim
        self.qk_head_dim = config.qk_nope_head_dim + config.qk_rope_head_dim
        self.num_key_value_groups = config.num_attention_heads // config.num_key_value_heads

        self.is_causal = True

        if self.q_lora_rank is None:
            self.q_proj = nn.Linear(self.hidden_size, self.num_heads * self.qk_head_dim, bias=False)
        else:
            self.q_a_proj = nn.Linear(self.hidden_size, config.q_lora_rank, bias=config.attention_bias)
            self.q_a_layernorm = DeepseekV2RMSNorm(config.q_lora_rank)
            self.q_b_proj = nn.Linear(config.q_lora_rank, self.num_heads * self.qk_head_dim, bias=False)

        self.kv_a_proj_with_mqa = nn.Linear(
            self.hidden_size,
            config.kv_lora_rank + config.qk_rope_head_dim,
            bias=config.attention_bias,
        )
        self.kv_a_layernorm = DeepseekV2RMSNorm(config.kv_lora_rank)
        self.kv_b_proj = nn.Linear(
            config.kv_lora_rank,
            self.num_heads * (self.qk_head_dim - self.qk_rope_head_dim + self.v_head_dim),
            bias=False,
        )

        self.o_proj = nn.Linear(
            self.num_heads * self.v_head_dim,
            self.hidden_size,
            bias=config.attention_bias,
        )

        self.scaling = self.qk_head_dim ** (-0.5)

    @deprecate_kwarg("past_key_value", new_name="past_key_values", version="4.58")
    def forward(
        self,
        hidden_states: torch.Tensor,
        attention_mask: Optional[torch.Tensor] = None,
        past_key_values: Optional[Cache] = None,
        cache_position: Optional[torch.LongTensor] = None,
        position_embeddings: Optional[tuple[torch.Tensor, torch.Tensor]] = None,
        position_ids: Optional[torch.Tensor] = None,
        **kwargs,
    ) -> tuple[torch.Tensor, Optional[torch.Tensor], Optional[tuple[torch.Tensor]]]:
        if "padding_mask" in kwargs:
            warnings.warn(
                "Passing `padding_mask` is deprecated and will be removed in v4.37. Please make sure use `attention_mask` instead.`"
            )
        batch_size, seq_length = hidden_states.shape[:-1]
        query_shape = (batch_size, seq_length, -1, self.qk_head_dim)
        key_shape = (batch_size, seq_length, -1, self.qk_nope_head_dim + self.v_head_dim)

        if self.q_lora_rank is None:
            q = self.q_proj(hidden_states)
        else:
            q = self.q_b_proj(self.q_a_layernorm(self.q_a_proj(hidden_states)))
        q = q.view(query_shape).transpose(1, 2)
        q_nope, q_pe = torch.split(q, [self.qk_nope_head_dim, self.qk_rope_head_dim], dim=-1)

        compressed_kv = self.kv_a_proj_with_mqa(hidden_states)
        k_nope, k_pe = torch.split(compressed_kv, [self.kv_lora_rank, self.qk_rope_head_dim], dim=-1)
        k_nope = self.kv_b_proj(self.kv_a_layernorm(k_nope)).view(key_shape).transpose(1, 2)
        k_nope, value_states = torch.split(k_nope, [self.qk_nope_head_dim, self.v_head_dim], dim=-1)

        k_pe = k_pe.view(batch_size, 1, seq_length, self.qk_rope_head_dim)
        q_pe, k_pe = apply_rotary_emb(q_pe, k_pe, position_embeddings.to(q_pe.device))

        k_pe = k_pe.expand(*k_nope.shape[:-1], -1)
        query_states = torch.cat((q_nope, q_pe), dim=-1)
        key_states = torch.cat((k_nope, k_pe), dim=-1)

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

        if self.config._attn_implementation == "flash_attention_2" and self.qk_head_dim != self.v_head_dim:
            value_states = F.pad(value_states, [0, self.qk_head_dim - self.v_head_dim])

        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,
        )

        if self.config._attn_implementation == "flash_attention_2" and self.qk_head_dim != self.v_head_dim:
            attn_output = attn_output[:, :, :, : self.v_head_dim]

        attn_output = attn_output.reshape(batch_size, seq_length, -1).contiguous()
        attn_output = self.o_proj(attn_output)
        return attn_output, attn_weights


class DeepseekV2DecoderLayer(GradientCheckpointingLayer):
    def __init__(self, config: DeepseekV2Config, layer_idx: int):
        super().__init__()
        self.hidden_size = config.hidden_size

        self.self_attn = DeepseekV2Attention(config=config, layer_idx=layer_idx)
        self.mlp = DeepseekV2MoE(config) if layer_idx >= config.first_k_dense_replace else DeepseekV2MLP(config)

        self.input_layernorm = DeepseekV2RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
        self.post_attention_layernorm = DeepseekV2RMSNorm(config.hidden_size, eps=config.rms_norm_eps)

    @deprecate_kwarg("past_key_value", new_name="past_key_values", version="4.58")
    def forward(
        self,
        hidden_states: torch.Tensor,
        attention_mask: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        past_key_values: Optional[Cache] = None,
        use_cache: Optional[bool] = False,
        cache_position: Optional[torch.LongTensor] = None,
        position_embeddings: Optional[tuple[torch.Tensor, torch.Tensor]] = None,  # necessary, but kept here for BC
        **kwargs: Unpack[TransformersKwargs],
    ) -> torch.Tensor:
        residual = hidden_states
        hidden_states = self.input_layernorm(hidden_states)
        # Self Attention
        hidden_states, _ = self.self_attn(
            hidden_states=hidden_states,
            attention_mask=attention_mask,
            position_ids=position_ids,
            past_key_values=past_key_values,
            use_cache=use_cache,
            cache_position=cache_position,
            position_embeddings=position_embeddings,
            **kwargs,
        )
        hidden_states = residual + hidden_states

        # Fully Connected
        residual = hidden_states
        hidden_states = self.post_attention_layernorm(hidden_states)
        hidden_states = self.mlp(hidden_states)
        hidden_states = residual + hidden_states
        return hidden_states


@auto_docstring
class DeepseekV2PreTrainedModel(PreTrainedModel):
    config: DeepseekV2Config
    base_model_prefix = "model"
    supports_gradient_checkpointing = True
    _no_split_modules = ["DeepseekV2DecoderLayer"]
    _skip_keys_device_placement = ["past_key_values"]
    _supports_flash_attn = True
    _supports_sdpa = True
    _supports_flex_attn = True
    _can_compile_fullgraph = False
    _supports_attention_backend = True
    _can_record_outputs = {
        "hidden_states": DeepseekV2DecoderLayer,
        "attentions": DeepseekV2Attention,
    }

    def _init_weights(self, module):
        super()._init_weights(module)
        if isinstance(module, DeepseekV2MoEGate):
            module.weight.data.normal_(mean=0.0, std=self.config.initializer_range)


@auto_docstring
class DeepseekV2Model(DeepseekV2PreTrainedModel):
    def __init__(self, config: DeepseekV2Config):
        super().__init__(config)
        self.padding_idx = config.pad_token_id
        self.vocab_size = config.vocab_size

        self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx)
        self.layers = nn.ModuleList(
            [DeepseekV2DecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)]
        )
        self.norm = DeepseekV2RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
        self.rotary_emb = DeepseekV2RotaryEmbedding(config=config)
        self.gradient_checkpointing = False

        # Initialize weights and apply final processing
        self.post_init()

    @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,
        cache_position: Optional[torch.LongTensor] = None,
        use_cache: Optional[bool] = 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: torch.Tensor = self.embed_tokens(input_ids)

        if use_cache and past_key_values is None:
            past_key_values = DynamicCache(config=self.config)

        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.Tensor = 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)

        causal_mask = create_causal_mask(
            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_values=past_key_values,
                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,
        )


@auto_docstring
class DeepseekV2ForCausalLM(DeepseekV2PreTrainedModel, GenerationMixin):
    _tied_weights_keys = ["lm_head.weight"]
    _tp_plan = {"lm_head": "colwise_rep"}
    _pp_plan = {"lm_head": (["hidden_states"], ["logits"])}

    def __init__(self, config):
        super().__init__(config)
        self.model = DeepseekV2Model(config)
        self.vocab_size = config.vocab_size
        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)

        # Initialize weights and apply final processing
        self.post_init()

    @can_return_tuple
    @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,
        labels: Optional[torch.LongTensor] = None,
        use_cache: Optional[bool] = None,
        cache_position: Optional[torch.LongTensor] = None,
        logits_to_keep: Union[int, torch.Tensor] = 0,
        **kwargs: Unpack[TransformersKwargs],
    ) -> CausalLMOutputWithPast:
        r"""
        Example:

        ```python
        >>> from transformers import AutoTokenizer, DeepseekV2ForCausalLM

        >>> model = DeepseekV2ForCausalLM.from_pretrained("meta-deepseek_v2/DeepseekV2-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-deepseek_v2/DeepseekV2-2-7b-hf")

        >>> prompt = "Hey, are you conscious? Can you talk to me?"
        >>> inputs = tokenizer(prompt, return_tensors="pt")

        >>> # Generate
        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
        ```"""
        outputs: BaseModelOutputWithPast = self.model(
            input_ids=input_ids,
            attention_mask=attention_mask,
            position_ids=position_ids,
            past_key_values=past_key_values,
            inputs_embeds=inputs_embeds,
            use_cache=use_cache,
            cache_position=cache_position,
            **kwargs,
        )

        hidden_states = outputs.last_hidden_state
        # Only compute necessary logits, and do not upcast them to float if we are not computing the loss
        slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep
        logits = self.lm_head(hidden_states[:, slice_indices, :])

        loss = None
        if labels is not None:
            loss = self.loss_function(logits=logits, labels=labels, vocab_size=self.config.vocab_size, **kwargs)

        return CausalLMOutputWithPast(
            loss=loss,
            logits=logits,
            past_key_values=outputs.past_key_values,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )


class DeepseekV2ForSequenceClassification(GenericForSequenceClassification, DeepseekV2PreTrainedModel):
    pass


__all__ = [
    "DeepseekV2PreTrainedModel",
    "DeepseekV2Model",
    "DeepseekV2ForCausalLM",
    "DeepseekV2ForSequenceClassification",
]