# coding=utf-8
# Copyright 2022 EleutherAI and the HuggingFace Inc. 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.
"""PyTorch INFLM model."""

import torch
from torch import nn
from transformers.models.llama.modeling_llama import (
    LlamaDecoderLayer,
    LlamaModel,
    LlamaForCausalLM
)
from .configuration_inflm import INFLMConfig

_CONFIG_FOR_DOC = "INFLMConfig"


class INFLMDecoderLayer(LlamaDecoderLayer):
    def __init__(self, config: INFLMConfig, layer_idx: int):
        super().__init__(config, layer_idx)
        self.input_layernorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
        self.post_attention_layernorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)


class INFLMModel(LlamaModel):
    config_class = INFLMConfig
    _no_split_modules = ["INFLMDecoderLayer"]
    
    def __init__(self, config: INFLMConfig):
        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([INFLMDecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)])
        self.norm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)

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


class INFLMForCausalLM(LlamaForCausalLM):
    _tied_weights_keys = ["lm_head.weight"]

    def __init__(self, config: INFLMConfig):
        super().__init__(config)
        self.model = INFLMModel(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()