import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AlpachinoNLP/Baichuan-13B-Instruction",trust_remote_code=True,use_fast=False)
model = AutoModelForCausalLM.from_pretrained("AlpachinoNLP/Baichuan-13B-Instruction",trust_remote_code=True ).half()
model.cuda()

def generate(histories,  max_new_tokens=2048, do_sample = True, top_p = 0.95, temperature = 0.35, repetition_penalty=1.1):
    prompt = ""
    for history in histories:
        history_with_identity = "\nHuman:" + history[0] + "\n\nAssistant:" + history[1]
        prompt += history_with_identity
    input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
    outputs = model.generate(
                    input_ids = input_ids,
                    max_new_tokens=max_new_tokens,
                    early_stopping=True,
                    do_sample=do_sample,
                    top_p=top_p, 
                    temperature=temperature,
                    repetition_penalty=repetition_penalty,
        )
    rets = tokenizer.batch_decode(outputs, skip_special_tokens=True)
    generate_text = rets[0].replace(prompt, "")
    return generate_text
    
with gr.Blocks() as demo:
    chatbot = gr.Chatbot()
    msg = gr.Textbox()
    clear = gr.Button("clear")

    def user(user_message, history):
        return "", history + [[user_message, ""]]

    def bot(history):
        print(history)
        bot_message = generate(history)
        history[-1][1] = bot_message
        return history

    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
        bot, chatbot, chatbot
    )
    clear.click(lambda: None, None, chatbot, queue=False)

if __name__ == "__main__":
    demo.launch(server_name="0.0.0.0")