BlueT / README.md
Darong's picture
Update README.md
b950206 verified
---
license: mit
language:
- ko
base_model:
- paust/pko-t5-base
pipeline_tag: translation
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
μ˜μ–΄-ν•œκ΅­μ–΄ λ²ˆμ—­ λͺ¨λΈμž…λ‹ˆλ‹€.
### Model Description
<!-- Provide a longer summary of what this model is. -->
paust/pko-t5-base λͺ¨λΈμ„ 기반으둜 μ˜μ–΄-ν•œκ΅­μ–΄ λ²ˆμ—­μ„ λ―Έμ„Έμ‘°μ •ν•œ λ²ˆμ—­ λͺ¨λΈμž…λ‹ˆλ‹€.
μ˜μ–΄->ν•œκ΅­μ–΄, ν•œκ΅­μ–΄->μ˜μ–΄ μ–‘λ°©ν–₯ λ²ˆμ—­μ„ μ§€μ›ν•˜λ©°, μ˜μ–΄->ν•œκ΅­μ–΄ λ²ˆμ—­ μ‹œ λ†’μž„λ§λ„
μ„€μ •ν•  수 μžˆμŠ΅λ‹ˆλ‹€.
- **Developed by:** [BlueAI]
- **Model type:** [t5.1.1.base]
- **Language(s) (NLP):** [Korean]
- **License:** [MIT]
- **Finetuned from model [optional]:** [paust/pko-t5-base]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
## How to Get Started with the Model
Use the code below to get started with the model.
```python
from transformers import pipeline, T5TokenizerFast
tokenizer_name = "paust/pko-t5-base"
tokenizer = T5TokenizerFast.from_pretrained(tokenizer_name)
model_path = 'Darong/BlueT'
translator = pipeline("translation", model=model_path, tokenizer=tokenizer, max_length=255)
# μ˜μ–΄ -> ν•œκ΅­μ–΄
prefix = "E2K: "
source = "This model is an English-Korean translation model."
target = translator(prefix + source)
print(target[0]['translation_text'])
# ν•œκ΅­μ–΄->μ˜μ–΄
prefix = "K2E: "
source = "이 λͺ¨λΈμ€ μ˜μ–΄-ν•œκ΅­μ–΄ λ²ˆμ—­ λͺ¨λΈμž…λ‹ˆλ‹€."
target = translator(prefix + source)
print(target[0]['translation_text'])
```
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
이 λͺ¨λΈμ€ AI Hub 및 자체 κ΅¬μΆ•ν•œ λ°μ΄ν„°λ‘œ ν•™μŠ΅λ˜μ—ˆμŠ΅λ‹ˆλ‹€.
μ˜μ–΄->ν•œκ΅­μ–΄ ν•™μŠ΅ 데이터 μˆ˜λŠ” 1800만 이상, ν•œκ΅­μ–΄->μ˜μ–΄ ν•™μŠ΅ 데이터 μˆ˜λŠ” 1200만 μ΄μƒμ˜ λ¬Έμž₯으둜 κ΅¬μΆ•λ˜μ—ˆμŠ΅λ‹ˆλ‹€.