kms7530's picture
Update README.md
fd7bdba verified
---
language:
- ko
library_name: transformers
license: apache-2.0
metrics:
- f1
pipeline_tag: text-classification
---
# roberta-base-infringement-detect
## Model Details
### Model Description
[klue/roberta-base](https://huggingface.co/klue/roberta-base) ๋ชจ๋ธ์„ ์ด์šฉํ•˜์—ฌ, ๋‘ ์ปจํ…์ธ ๊ฐ„์˜ ์œ ์‚ฌ์—ฌ๋ถ€๋ฅผ ํ™•์ธํ•˜๋Š” ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค.
## Train
์ž์ฒด๊ตฌ์ถ•๋œ 1,310๊ฐœ์˜ ์ฐธ์ธ ์œ ์‚ฌ ์ปจํ…์ธ  ์Œ์„ ์ด์šฉํ•˜์—ฌ, ์…”ํ”Œ ํ›„ ์ฐธ/๊ฑฐ์ง“ ๋น„์œจ 1:2์ธ ๋ฐ์ดํ„ฐ์…‹์„ ์ƒ์„ฑํ•˜์—ฌ ํ•™์Šต์‹œ์ผฐ์Šต๋‹ˆ๋‹ค.
์ด์™ธ์˜ ํ•™์Šต์‹œ ํŒŒ๋ผ๋ฏธํ„ฐ๋Š” ๋‹ค์Œ๊ณผ ๊ฐ™์Šต๋‹ˆ๋‹ค.
| Parameter | Value |
| ------------------ | ----- |
| `train_batch_size` | 16 |
| `num_train_epochs` | 5 |
| `weight_decay` | 0.01 |
| `learning_rate` | 2e-5 |
## How to use
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
model_name = "kms7530/roberta-base-infringement-detect"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
```
๋ชจ๋ธ์— ์ถ”๋ก  ์‹œ ๋‹ค์Œ๊ณผ ๊ฐ™์ด ์ž…๋ ฅํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
```plain
[CLS]\
[unused0]<ORIGINAL_CONTENT_TITLE>\
[unused1]<ORIGINAL_CONTENT>[SEP] \
[unused0]<TEST_CONTENT_TITLE>\
[unused1]<TEST_CONTENT>[SEP]
```