liutiedong / goat Goto Github PK

def generate_prompt_with_history(text,history,tokenizer,max_length=2048):
    prompt = "The following is a conversation between a human and an AI assistant named Goat. The human and the AI assistant take turns chatting. Human statements start with [|Human|] and AI assistant statements start with [|AI|]. The AI assistant always provides responses in as much detail as possible, and in Markdown format. The AI assistant always declines to engage with topics, questions and instructions related to unethical, controversial, or sensitive issues. Complete the transcript in exactly that format.\n[|Human|]Hello!\n[|AI|]Hi!"   
    history = ["\n[|Human|]{}\n[|AI|]{}".format(x[0],x[1]) for x in history]
    history.append("\n[|Human|]{}\n[|AI|]".format(text))
    history_text = ""
    flag = False
    for x in history[::-1]:
        if tokenizer(prompt+history_text+x, return_tensors="pt")['input_ids'].size(-1) <= max_length:
            history_text = x + history_text
            flag = True
        else:
            break
    if flag:
        return  prompt+history_text,tokenizer(prompt+history_text, return_tensors="pt")
    else:
        return None


def is_stop_word_or_prefix(s: str, stop_words: list) -> bool:
    for stop_word in stop_words:
        if s.endswith(stop_word):
            return True
        for i in range(1, len(stop_word)):
            if s.endswith(stop_word[:i]):
                return True
    return False