from typing import TYPE_CHECKING, Any, Dict

from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
from trl import AutoModelForCausalLMWithValueHead

from ..extras.constants import MOD_SUPPORTED_MODELS
from ..extras.logging import get_logger
from ..extras.misc import count_parameters, get_current_device, try_download_model_from_ms
from .adapter import init_adapter
from .patcher import patch_config, patch_model, patch_tokenizer, patch_valuehead_model
from .utils.misc import load_valuehead_params, register_autoclass


if TYPE_CHECKING:
    from transformers import PretrainedConfig, PreTrainedModel, PreTrainedTokenizer

    from ..hparams import FinetuningArguments, ModelArguments


logger = get_logger(__name__)


def _get_init_kwargs(model_args: "ModelArguments") -> Dict[str, Any]:
    r"""
    Gets arguments to load config/tokenizer/model.

    Note: including inplace operation of model_args.
    """
    model_args.model_name_or_path = try_download_model_from_ms(model_args)
    return {
        "trust_remote_code": True,
        "cache_dir": model_args.cache_dir,
        "revision": model_args.model_revision,
        "token": model_args.hf_hub_token,
    }


def load_tokenizer(model_args: "ModelArguments") -> "PreTrainedTokenizer":
    r"""
    Loads pretrained tokenizer.
    """
    init_kwargs = _get_init_kwargs(model_args)
    try:
        tokenizer = AutoTokenizer.from_pretrained(
            model_args.model_name_or_path,
            use_fast=model_args.use_fast_tokenizer,
            split_special_tokens=model_args.split_special_tokens,
            padding_side="right",
            **init_kwargs,
        )
    except ValueError:  # try the fast one
        tokenizer = AutoTokenizer.from_pretrained(
            model_args.model_name_or_path,
            use_fast=True,
            padding_side="right",
            **init_kwargs,
        )

    patch_tokenizer(tokenizer)
    return tokenizer


def load_config(model_args: "ModelArguments") -> "PretrainedConfig":
    r"""
    Loads model config.
    """
    init_kwargs = _get_init_kwargs(model_args)
    return AutoConfig.from_pretrained(model_args.model_name_or_path, **init_kwargs)


def load_model(
    tokenizer: "PreTrainedTokenizer",
    model_args: "ModelArguments",
    finetuning_args: "FinetuningArguments",
    is_trainable: bool = False,
    add_valuehead: bool = False,
) -> "PreTrainedModel":
    r"""
    Loads pretrained model.
    """
    init_kwargs = _get_init_kwargs(model_args)
    config = load_config(model_args)
    patch_config(config, tokenizer, model_args, init_kwargs, is_trainable)

    model = None
    if is_trainable and model_args.use_unsloth:
        from unsloth import FastLanguageModel  # type: ignore

        unsloth_kwargs = {
            "model_name": model_args.model_name_or_path,
            "max_seq_length": model_args.model_max_length,
            "dtype": model_args.compute_dtype,
            "load_in_4bit": model_args.quantization_bit == 4,
            "token": model_args.hf_hub_token,
            "device_map": {"": get_current_device()},
            "rope_scaling": getattr(config, "rope_scaling", None),
            "fix_tokenizer": False,
            "trust_remote_code": True,
        }
        try:
            model, _ = FastLanguageModel.from_pretrained(**unsloth_kwargs)
        except NotImplementedError:
            logger.warning("Unsloth does not support model type {}.".format(getattr(config, "model_type", None)))
            model_args.use_unsloth = False

        if model_args.adapter_name_or_path:
            model_args.adapter_name_or_path = None
            logger.warning("Unsloth does not support loading adapters.")

    if model is None:
        init_kwargs["config"] = config
        init_kwargs["pretrained_model_name_or_path"] = model_args.model_name_or_path

        if model_args.mixture_of_depths == "load":
            from MoD import AutoMoDModelForCausalLM

            model = AutoMoDModelForCausalLM.from_pretrained(**init_kwargs)
        else:
            model = AutoModelForCausalLM.from_pretrained(**init_kwargs)

        if model_args.mixture_of_depths == "convert":
            from MoD import apply_mod_to_hf

            if getattr(config, "model_type", None) not in MOD_SUPPORTED_MODELS:
                raise ValueError("Current model is not supported by mixture-of-depth.")

            model = apply_mod_to_hf(model)
            model = model.to(model_args.compute_dtype)

    patch_model(model, tokenizer, model_args, is_trainable)
    register_autoclass(config, model, tokenizer)

    model = init_adapter(model, model_args, finetuning_args, is_trainable)

    if add_valuehead:
        model = AutoModelForCausalLMWithValueHead.from_pretrained(model)
        patch_valuehead_model(model)

        if model_args.adapter_name_or_path is not None:
            vhead_path = model_args.adapter_name_or_path[-1]
        else:
            vhead_path = model_args.model_name_or_path

        vhead_params = load_valuehead_params(vhead_path, model_args)
        if vhead_params is not None:
            model.load_state_dict(vhead_params, strict=False)
            logger.info("Loaded valuehead from checkpoint: {}".format(vhead_path))

    if not is_trainable:
        model.requires_grad_(False)
        model.eval()
    else:
        model.train()

    trainable_params, all_param = count_parameters(model)
    if is_trainable:
        param_stats = "trainable params: {:d} || all params: {:d} || trainable%: {:.4f}".format(
            trainable_params, all_param, 100 * trainable_params / all_param
        )
    else:
        param_stats = "all params: {:d}".format(all_param)
    logger.info(param_stats)

    if model_args.print_param_status:
        for name, param in model.named_parameters():
            print(
                "name: {}, dtype: {}, device: {}, trainable: {}".format(
                    name, param.dtype, param.device, param.requires_grad
                )
            )

    return model