import argparse
import random
import warnings
import numpy as np
from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
from model.model_minimind import MiniMindConfig, MiniMindForCausalLM
from model.model_lora import *

warnings.filterwarnings('ignore')


def init_model(args):
    transformers_model_path = './MiniMind2'
    tokenizer = AutoTokenizer.from_pretrained(transformers_model_path)
    model = AutoModelForCausalLM.from_pretrained(transformers_model_path, trust_remote_code=True)
    print(f'MiniMind模型参数量: {sum(p.numel() for p in model.parameters() if p.requires_grad) / 1e6:.2f}M(illion)')
    return model.eval().to(args.device), tokenizer


# 设置可复现的随机种子
def setup_seed(seed):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)
    torch.backends.cudnn.deterministic = True
    torch.backends.cudnn.benchmark = False


def main():
    print("开始加载模型")
    parser = argparse.ArgumentParser(description="Chat with MiniMind")
    parser.add_argument('--lora_name', default='None', type=str)
    parser.add_argument('--out_dir', default='out', type=str)
    parser.add_argument('--temperature', default=0.85, type=float)
    parser.add_argument('--top_p', default=0.85, type=float)
    parser.add_argument('--device', default='cuda' if torch.cuda.is_available() else 'cpu', type=str)
    # 此处max_seq_len（最大输出长度）并不意味模型具有对应的长文本的性能，仅防止QA出现被截断的问题
    # MiniMind2-moe (145M)：(hidden_size=640, num_hidden_layers=8, use_moe=True)
    # MiniMind2-Small (26M)：(hidden_size=512, num_hidden_layers=8)
    # MiniMind2 (104M)：(hidden_size=768, num_hidden_layers=16)
    parser.add_argument('--hidden_size', default=512, type=int)
    parser.add_argument('--num_hidden_layers', default=8, type=int)
    parser.add_argument('--max_seq_len', default=8192, type=int)
    parser.add_argument('--use_moe', default=False, type=bool)
    # 携带历史对话上下文条数
    # history_cnt需要设为偶数，即【用户问题, 模型回答】为1组；设置为0时，即当前query不携带历史上文
    # 模型未经过外推微调时，在更长的上下文的chat_template时难免出现性能的明显退化，因此需要注意此处设置
    parser.add_argument('--history_cnt', default=0, type=int)
    parser.add_argument('--load', default=0, type=int, help="0: 原生torch权重，1: transformers加载")
    parser.add_argument('--model_mode', default=1, type=int,
                        help="0: 预训练模型，1: SFT-Chat模型，2: RLHF-Chat模型，3: Reason模型，4: RLAIF-Chat模型")
    args = parser.parse_args()

    model, tokenizer = init_model(args)

    streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

    messages = []
    for prompt in iter(lambda: input('👶: '), ''):
        if prompt == "exit":
            break
        setup_seed(random.randint(0, 2048))

        messages.append({"role": "user", "content": prompt})

        new_prompt = tokenizer.apply_chat_template(
            messages,
            tokenize=False,
            add_generation_prompt=True
        ) if args.model_mode != 0 else (tokenizer.bos_token + prompt)

        inputs = tokenizer(
            new_prompt,
            return_tensors="pt",
            truncation=True
        ).to(args.device)

        print('🤖️: ', end='')
        generated_ids = model.generate(
            inputs["input_ids"],
            max_new_tokens=args.max_seq_len,
            num_return_sequences=1,
            do_sample=True,
            attention_mask=inputs["attention_mask"],
            pad_token_id=tokenizer.pad_token_id,
            eos_token_id=tokenizer.eos_token_id,
            streamer=streamer,
            top_p=args.top_p,
            temperature=args.temperature
        )

        response = tokenizer.decode(generated_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
        messages.append({"role": "assistant", "content": response})
        print('\n')


if __name__ == "__main__":
    main()