Personagpt

🚀 多人格對話代理（PersonaGPT）

PersonaGPT 是一個開放領域的對話代理，旨在完成兩項任務：

1. 根據輸入的個性事實（機器人的“人設”配置文件）解碼出“個性化”回覆。
2. 通過“動作代碼”（例如，“談論工作”“詢問喜歡的音樂”）將“輪次級目標”融入其回覆中。

它基於 [GPT - 2](https://github.com/openai/gpt - 2) 架構的 [DialoGPT - medium](https://huggingface.co/microsoft/DialoGPT - medium) 預訓練模型構建。該模型在 Persona - Chat 數據集上進行訓練，並添加了特殊標記，以便在雙人對話中更好地區分對話歷史和個性特徵。此外，還使用了一些主動學習方法來訓練模型，使其能夠根據輪次級目標進行“可控”解碼。

📚 完整倉庫

預處理、訓練和實現細節可在 personaGPT 倉庫 中找到。

🚀 快速開始

📦 安裝

本項目依賴於 transformers 和 torch 庫，你可以使用以下命令進行安裝：

pip install transformers torch

💻 使用示例

基礎用法

1. 加載模型並定義一些輔助函數：

from transformers import GPT2Tokenizer, GPT2LMHeadModel
import torch
tokenizer = GPT2Tokenizer.from_pretrained("af1tang/personaGPT")
model = GPT2LMHeadModel.from_pretrained("af1tang/personaGPT")
if torch.cuda.is_available():
    model = model.cuda()
## utility functions ##
flatten = lambda l: [item for sublist in l for item in sublist]

def to_data(x):
    if torch.cuda.is_available():
        x = x.cpu()
    return x.data.numpy()

def to_var(x):
    if not torch.is_tensor(x):
        x = torch.Tensor(x)
    if torch.cuda.is_available():
        x = x.cuda()
    return x

def display_dialog_history(dialog_hx):
    for j, line in enumerate(dialog_hx):
        msg = tokenizer.decode(line)
        if j %2 == 0:
            print(">> User: "+ msg)
        else:
            print("Bot: "+msg)
            print()

def generate_next(bot_input_ids, do_sample=True, top_k=10, top_p=.92,
                  max_length=1000, pad_token=tokenizer.eos_token_id):
    full_msg = model.generate(bot_input_ids, do_sample=True,
                                              top_k=top_k, top_p=top_p, 
                                              max_length=max_length, pad_token_id=tokenizer.eos_token_id)
    msg = to_data(full_msg.detach()[0])[bot_input_ids.shape[-1]:]
    return msg

2. 為你的聊天機器人夥伴設置一組個性特徵：

# get personality facts for conversation
personas = []
for i in range(3):
    response = input(">> Fact %d: "%(i+1))+ tokenizer.eos_token
    personas.append(response)
personas = tokenizer.encode(''.join(['<|p2|>'] + personas + ['<|sep|>'] + ['<|start|>']))

3. 個性化對話生成：使用以下循環與模型進行交互：

# converse for 8 turns
dialog_hx = []
for step in range(8):
    # encode the user input
    user_inp = tokenizer.encode(input(">> User: ") + tokenizer.eos_token)
    # append to the chat history
    dialog_hx.append(user_inp)
        
    # generated a response while limiting the total chat history to 1000 tokens, 
    bot_input_ids = to_var([personas + flatten(dialog_hx)]).long()
    msg = generate_next(bot_input_ids)
    dialog_hx.append(msg)
    print("Bot: {}".format(tokenizer.decode(msg, skip_special_tokens=True)))

以下是個性化解碼的示例：

4. 可控回覆生成：使用以下程序與模型進行交互：

## available actions ##
action_space = [ 'ask about kids.', "ask about pets.", 'talk about work.', 
               'ask about marital status.', 'talk about travel.', 'ask about age and gender.',
        'ask about hobbies.', 'ask about favorite food.', 'talk about movies.', 
        'talk about music.', 'talk about politics.']
# converse for 8 turns
dialog_hx = []
for step in range(8):
    # choose an action
    act = None
    while act not in action_space:
        display_dialog_history(dialog_hx)
        print()
        print(" actions: ")
        for k,v in enumerate(action_space): print(k,v)
        try:
            act = action_space[int(input(" input [0-10]: " ))]
        except:
            act = None
    print()
    # format into prefix code
    action_prefix = tokenizer.encode(''.join(['<|act|> '] + [act] + ['<|p1|>'] + [] + ['<|sep|>'] + ['<|start|>']))
    bot_input_ids = to_var([action_prefix + flatten(dialog_hx)]).long()
    
    # generate query conditioned on action
    msg = generate_next(bot_input_ids, top_k=top_k, top_p=top_p, max_length=max_length)
    dialog_hx.append(msg)
    
    # generate bot response
    bot_input_ids = to_var([personas+ flatten(dialog_hx)]).long()
    msg = generate_next(bot_input_ids, top_k=top_k, top_p=top_p, max_length=max_length)
    dialog_hx.append(msg)
display_dialog_history(dialog_hx)

以下是可控回覆生成的示例：

📄 許可證

本項目採用 GPL - 3.0 許可證。