---
language: ko
tags:
  - gpt2
  - conversational
license: cc-by-nc-sa 4.0
---
## Ko-DialoGPT


### How to use
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-small")
model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-small")

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("BOT: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
```

### Reference
* [SKT-KoGPT2](https://huggingface.co/skt/kogpt2-base-v2)
* [KETI R&D 데이터](https://aihub.or.kr/opendata/keti-data/recognition-laguage/KETI-02-008)
* [한국어 대화 요약](https://aihub.or.kr/aidata/30714)