Instructions to use BM-K/KoMiniLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BM-K/KoMiniLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="BM-K/KoMiniLM")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("BM-K/KoMiniLM") model = AutoModel.from_pretrained("BM-K/KoMiniLM") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -32,9 +32,6 @@ Self-Attention Distribution and Self-Attention Value-Relation [[Wang et al., 202
|
|
| 32 |
|Data|News comments|News article|
|
| 33 |
|:----:|:----:|:----:|
|
| 34 |
|size|10G|10G|
|
| 35 |
-
> **Note**<br>
|
| 36 |
-
> - Performance can be further improved by adding wiki data to training.
|
| 37 |
-
> - The crawling and preprocessing code for the *News article* is [here](https://github.com/2unju/DaumNewsCrawler).
|
| 38 |
|
| 39 |
### Config
|
| 40 |
- **KoMiniLM-23M**
|
|
|
|
| 32 |
|Data|News comments|News article|
|
| 33 |
|:----:|:----:|:----:|
|
| 34 |
|size|10G|10G|
|
|
|
|
|
|
|
|
|
|
| 35 |
|
| 36 |
### Config
|
| 37 |
- **KoMiniLM-23M**
|