File size: 1,798 Bytes
5222660 53cce06 d4d30d2 f9e1ede d4d30d2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
---
pipeline_tag: conversational
language:
- ko
tags:
- conversational
---
### How to use
Now we are ready to try out how the model works as a chatting partner!
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
tokenizer = AutoTokenizer.from_pretrained("keonju/chat_bot")
model = AutoModelForCausalLM.from_pretrained("keonju/chat_bot")
# Let's chat for 5 lines
for step in range(5):
message = input("MESSAGE: ")
if message in ["", "q"]: # if the user doesn't wanna talk
break
# encode the new user input, add the eos_token and return a tensor in Pytorch
new_user_input_ids = tokenizer.encode(message + 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,
if (trained):
chat_history_ids = model.generate(
bot_input_ids,
max_length=1000,
pad_token_id=tokenizer.eos_token_id,
no_repeat_ngram_size=3,
do_sample=True,
top_k=100,
top_p=0.7,
temperature = 0.8,
)
else:
chat_history_ids = model.generate(
bot_input_ids,
max_length=1000,
pad_token_id=tokenizer.eos_token_id,
no_repeat_ngram_size=3
)
# 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)))
|