Instructions to use monologg/kobert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use monologg/kobert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="monologg/kobert")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("monologg/kobert") model = AutoModel.from_pretrained("monologg/kobert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from monologg/kobert: direct link, hf CLI and curl.
- Browser
- Download file 449 Bytes
-
https://huggingface.co/monologg/kobert/resolve/main/README.md
- Command line
-
hf download hf://monologg/kobert/README.md
-
curl -L -o README.md https://huggingface.co/monologg/kobert/resolve/main/README.md
449 Bytes
| license: apache-2.0 | |
| language: | |
| - ko | |
| inference: false | |
| # KoBERT | |
| ## How to use | |
| > If you want to import KoBERT tokenizer with `AutoTokenizer`, you should give `trust_remote_code=True`. | |
| ```python | |
| from transformers import AutoModel, AutoTokenizer | |
| model = AutoModel.from_pretrained("monologg/kobert") | |
| tokenizer = AutoTokenizer.from_pretrained("monologg/kobert", trust_remote_code=True) | |
| ``` | |
| ## Reference | |
| - https://github.com/SKTBrain/KoBERT | |