|
--- |
|
language: ko |
|
license: apache-2.0 |
|
--- |
|
|
|
# team-lucid/t5-v1_1-large-ko |
|
|
|
[Google's T5](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) Version 1.1 that trained on korean corpus |
|
|
|
t5-v1_1-large-koμ νκ΅μ΄ μ½νΌμ€μμ νμ΅λ t5 v1.1 λͺ¨λΈμ
λλ€. |
|
|
|
OOVμ λ§κΈ° μν΄ BBPEλ₯Ό μ¬μ©νμμΌλ©°, HyperCLOVAμμ ννμ λΆμμ΄ μ±λ₯μ λνλλ° λμμ΄ λλ κ²μ λ³΄κ³ ν ν¬λμ΄μ νμ΅ κ³Όμ μμ MeCabμ μ΄μ©ν΄ ννμκ° μ΄μνκ² ν ν°νλμ§ μλλ‘ νμμ΅λλ€. |
|
|
|
μ΄ μ°κ΅¬λ ꡬκΈμ TPU Research Cloud(TRC)λ₯Ό ν΅ν΄ μ§μλ°μ Cloud TPUλ‘ νμ΅λμμ΅λλ€. |
|
|
|
## Usage |
|
```python |
|
from transformers import AutoTokenizer, T5ForConditionalGeneration |
|
|
|
tokenizer = AutoTokenizer.from_pretrained('team-lucid/t5-v1_1-large-ko') |
|
model = T5ForConditionalGeneration.from_pretrained('team-lucid/t5-v1_1-large-ko') |
|
``` |