from transformers import AutoTokenizer,TextStreamer,TextIteratorStreamer
from auto_gptq import AutoGPTQForCausalLM


class TaiwanLLaMaGPTQ:
    def __init__(self, model_dir):
        self.tokenizer = AutoTokenizer.from_pretrained(model_dir, use_fast=True)
        self.model = AutoGPTQForCausalLM.from_quantized(model_dir,
            trust_remote_code=True,
            use_safetensors=True,
            device_map="auto",
            use_triton=False,
            strict=False)
        self.chat_history = []
        self.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."""

        self.streamer = TextStreamer(self.tokenizer, skip_prompt=True, skip_special_tokens=True)
        self.thread_streamer = TextIteratorStreamer(self.tokenizer, skip_special_tokens=True)
    def get_prompt(self, message: str, chat_history: list[tuple[str, str]]) -> str:
        texts = [f'[INST] <<SYS>>\n{self.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)

    def generate(self, message: str):
        prompt = self.get_prompt(message, self.chat_history)
        tokens = self.tokenizer(prompt, return_tensors='pt').input_ids
        generate_ids = self.model.generate(input_ids=tokens.cuda(), max_new_tokens=4096, streamer=self.streamer)
        output = self.tokenizer.decode(generate_ids[0, len(tokens[0]):-1]).strip()
        self.chat_history.append([message, output])
        return output
    
    def thread_generate(self, message:str):
        from threading import Thread
        prompt = self.get_prompt(message, self.chat_history)
        inputs = self.tokenizer(prompt, return_tensors="pt")

        generation_kwargs = dict(
            inputs=inputs.input_ids.cuda(),
            attention_mask=inputs.attention_mask,
            temperature=0.1,
            max_new_tokens=1024,
            streamer=self.thread_streamer,
        )

        # Run generation on separate thread to enable response streaming.
        thread = Thread(target=self.model.generate, kwargs=generation_kwargs)
        thread.start()
        for new_text in self.thread_streamer:
            yield new_text

        thread.join()

inferencer = TaiwanLLaMaGPTQ("weiren119/Taiwan-LLaMa-v1.0-4bits-GPTQ")


s = ''
while True:
    s = input("User: ")
    if s != '':
        print ('Answer:')
        print (inferencer.generate(s))
        print ('-'*80)