import transformers
import torch
from transformers import AutoTokenizer, TextStreamer

# Use the same tokenizer from the source model
model_id="weiren119/traditional_chinese_qlora_llama2_13b_merged"
tokenizer = AutoTokenizer.from_pretrained(original_model_path, use_fast=False)

# Load fine-tuned model, you can replace this with your own model
model = AutoPeftModelForCausalLM.from_pretrained(
        model_id,
        load_in_4bit=model_id.endswith("4bit"),
        torch_dtype=torch.float16,
        device_map='auto'
)

system_prompt = """You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

            If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."""




def get_prompt(message: str, chat_history: list[tuple[str, str]]) -> str:
    texts = [f'[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n']
    for user_input, response in chat_history:
        texts.append(f'{user_input.strip()} [/INST] {response.strip()} </s><s> [INST] ')
    texts.append(f'{message.strip()} [/INST]')
    return ''.join(texts)


print ("="*100)
print ("-"*80)
print ("Have a try!")

s = ''
chat_history = []
while True:
    s = input("User: ")
    if s != '':
        prompt = get_prompt(s, chat_history)
        print ('Answer:')
        tokens = tokenizer(prompt, return_tensors='pt').input_ids
        #generate_ids = model.generate(tokens.cuda(), max_new_tokens=4096, streamer=streamer)
        generate_ids = model.generate(input_ids=tokens.cuda(), max_new_tokens=4096, streamer=streamer)
        output = tokenizer.decode(generate_ids[0, len(tokens[0]):-1]).strip()
        chat_history.append([s, output])
        print ('-'*80)