Views
No views yet
| Count | Domain | |
| Chinese Persona Chat (CPC) | 23,000 | Open |
| LCCC | 11,987,759 | Open |
| Emotional STC (ESTC) | 899,207 | Open |
| KdConv | 3,000 | Movie, Music, Travel |
[CLS] 对话历史：<history> 知识：<knowledge> [SEP][CLS] <response> [SEP]1from transformers import BertTokenizer, BartForConditionalGeneration
2# Note that tokenizer is an object of BertTokenizer, instead of BartTokenizer
3tokenizer = BertTokenizer.from_pretrained("HIT-TMG/dialogue-bart-base-chinese")
4model = BartForConditionalGeneration.from_pretrained("HIT-TMG/dialogue-bart-base-chinese")
5# an example from CPC dev data
6history = ["可以 认识 一下 吗 ？", "当然 可以 啦 ， 你好 。", "嘿嘿 你好 ， 请问 你 最近 在 忙 什么 呢 ？", "我 最近 养 了 一只 狗狗 ， 我 在 训练 它 呢 。"]
7history_str = "对话历史：" + tokenizer.sep_token.join(history)
8input_ids = tokenizer(history_str, return_tensors='pt').input_ids
9output_ids = model.generate(input_ids)[0]
10print(tokenizer.decode(output_ids, skip_special_tokens=True))