Downloads · 30 days
23.6K
0% of all-time downloads
kobert
monologg/kobert
kobert is a feature extraction model from monologg. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as apache-2.0.
If you want to import KoBERT tokenizer with AutoTokenizer, you should give trustremotecode=True.
All-time downloads
9.5M
Public
Parameters
92.2M
1.5 GB on disk
Likes
20
Public
Repo makeup
Click a slice to open those files.
.bin369 MB · 33%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Aug 21, 2024
- SHA
- 38279184
Model card
From the Hugging Face model README
KoBERT
How to use
If you want to import KoBERT tokenizer with
AutoTokenizer, you should givetrust_remote_code=True.
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("monologg/kobert")
tokenizer = AutoTokenizer.from_pretrained("monologg/kobert", trust_remote_code=True)
Reference
- Task
- Feature Extraction
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Languages
- ko
- Created
- Mar 2, 2022
- Updated
- Aug 21, 2024