Update README.md
Browse files
README.md
CHANGED
|
@@ -4,4 +4,52 @@ language:
|
|
| 4 |
- ko
|
| 5 |
tags:
|
| 6 |
- conversational
|
| 7 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- ko
|
| 5 |
tags:
|
| 6 |
- conversational
|
| 7 |
+
---
|
| 8 |
+
### How to use
|
| 9 |
+
|
| 10 |
+
Now we are ready to try out how the model works as a chatting partner!
|
| 11 |
+
|
| 12 |
+
```python
|
| 13 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 14 |
+
import torch
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
|
| 18 |
+
model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
|
| 19 |
+
|
| 20 |
+
# Let's chat for 5 lines
|
| 21 |
+
for step in range(5):
|
| 22 |
+
message = input("MESSAGE: ")
|
| 23 |
+
|
| 24 |
+
if message in ["", "q"]: # if the user doesn't wanna talk
|
| 25 |
+
break
|
| 26 |
+
|
| 27 |
+
# encode the new user input, add the eos_token and return a tensor in Pytorch
|
| 28 |
+
new_user_input_ids = tokenizer.encode(message + tokenizer.eos_token, return_tensors='pt')
|
| 29 |
+
|
| 30 |
+
# append the new user input tokens to the chat history
|
| 31 |
+
bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
# generated a response while limiting the total chat history to 1000 tokens,
|
| 35 |
+
if (trained):
|
| 36 |
+
chat_history_ids = model.generate(
|
| 37 |
+
bot_input_ids,
|
| 38 |
+
max_length=1000,
|
| 39 |
+
pad_token_id=tokenizer.eos_token_id,
|
| 40 |
+
no_repeat_ngram_size=3,
|
| 41 |
+
do_sample=True,
|
| 42 |
+
top_k=100,
|
| 43 |
+
top_p=0.7,
|
| 44 |
+
temperature = 0.8,
|
| 45 |
+
)
|
| 46 |
+
else:
|
| 47 |
+
chat_history_ids = model.generate(
|
| 48 |
+
bot_input_ids,
|
| 49 |
+
max_length=1000,
|
| 50 |
+
pad_token_id=tokenizer.eos_token_id,
|
| 51 |
+
no_repeat_ngram_size=3
|
| 52 |
+
)
|
| 53 |
+
|
| 54 |
+
# pretty print last ouput tokens from bot
|
| 55 |
+
print("DialoGPT: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
|