Downloads · 30 days
21
2% of all-time downloads
bert-base-v1-sports
emeraldgoose/bert-base-v1-sports
bert-base-v1-sports is a fill-mask model from emeraldgoose. Use it when you need the model to fill a missing word. It is set up for transformers.
위키피디아(스포츠) dataset 구축을 진행하면서 얻은 문장을 통해 bert 사전학습을 진행
All-time downloads
959
Public
Parameters
91.6M
2.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin367 MB · 50%
Parameter types
How the weights are stored.
F3291.6M · 100%
Try a prompt
Model card
From the Hugging Face model README
Data-annotation-nlp-10 (BoostCamp AI)
위키피디아(스포츠) dataset 구축을 진행하면서 얻은 문장을 통해 bert 사전학습을 진행
How to use
from transformers import AutoTokenizer, BertForMaskedLM
model = BertForMaskedLM.from_pretrained("emeraldgoose/bert-base-v1-sports")
tokenizer = AutoTokenizer.from_pretrained("emeraldgoose/bert-base-v1-sports")
text = "산악 자전거 경기는 상대적으로 새로운 [MASK] 1990년대에 활성화 되었다."
inputs = tokenizer.encode(text, return_tensors='pt')
model.eval()
outputs = model(inputs)['logits']
predict = outputs.argmax(-1)[0]
print(tokenizer.decode(predict))
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- Languages
- ko
- Created
- Mar 2, 2022
- Updated
- Feb 16, 2025