42 lines
1018 B
Markdown
42 lines
1018 B
Markdown
|
## How to use
|
||
|
|
```python
|
||
|
|
import transformers
|
||
|
|
|
||
|
|
model = transformers.GPT2LMHeadModel.from_pretrained("lbox/lcube-base")
|
||
|
|
tokenizer = transformers.AutoTokenizer.from_pretrained(
|
||
|
|
"lbox/lcube-base",
|
||
|
|
bos_token="[BOS]",
|
||
|
|
unk_token="[UNK]",
|
||
|
|
pad_token="[PAD]",
|
||
|
|
mask_token="[MASK]",
|
||
|
|
)
|
||
|
|
|
||
|
|
text = "피고인은 불상지에 있는 커피숍에서, 피해자 B으로부터"
|
||
|
|
model_inputs = tokenizer(text,
|
||
|
|
max_length=1024,
|
||
|
|
padding=True,
|
||
|
|
truncation=True,
|
||
|
|
return_tensors='pt')
|
||
|
|
out = model.generate(
|
||
|
|
model_inputs["input_ids"],
|
||
|
|
max_new_tokens=150,
|
||
|
|
pad_token_id=tokenizer.pad_token_id,
|
||
|
|
use_cache=True,
|
||
|
|
repetition_penalty=1.2,
|
||
|
|
top_k=5,
|
||
|
|
top_p=0.9,
|
||
|
|
temperature=1,
|
||
|
|
num_beams=2,
|
||
|
|
)
|
||
|
|
tokenizer.batch_decode(out)
|
||
|
|
```
|
||
|
|
|
||
|
|
For more information please visit <https://github.com/lbox-kr/lbox_open>.
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
## Licensing Information
|
||
|
|
|
||
|
|
Copyright 2022-present LBox Co. Ltd.
|
||
|
|
|
||
|
|
Licensed under the CC BY-NC-ND 4.0
|