西班牙语对话的微调DialoGPT模型

该模型是从原始 DialoGPT-medium 模型上通过西班牙电影和电视剧字幕进行微调的，数据来自于出色的 OpenSubtitle dataset 。

DialoGPT论文： https://arxiv.org/abs/1911.00536

模型的一些示例对话：

使用模型

用于尝试模型的示例代码（直接从 DialoGPT-medium 模型卡片中取出）：

from transformers import AutoModelWithLMHead, AutoTokenizer
import torch


tokenizer = AutoTokenizer.from_pretrained("emre/spanish-dialoGPT")
model = AutoModelWithLMHead.from_pretrained("emre/spanish-dialoGPT")

# Let's chat for 5 lines
for step in range(5):
    # encode the new user input, add the eos_token and return a tensor in Pytorch
    new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')

    # append the new user input tokens to the chat history
    bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids

    # generated a response while limiting the total chat history to 1000 tokens, 
    chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)

    # pretty print last ouput tokens from bot
    print("DialoGPT: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))