Instructions to use demdecuong/stroke_sup_simcse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use demdecuong/stroke_sup_simcse with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="demdecuong/stroke_sup_simcse")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("demdecuong/stroke_sup_simcse") model = AutoModel.from_pretrained("demdecuong/stroke_sup_simcse") - Notebooks
- Google Colab
- Kaggle
demdecuong commited on
Commit ·
28e6817
1
Parent(s): f4e85a4
update readme
Browse files
README.md
CHANGED
|
@@ -1,5 +1,8 @@
|
|
| 1 |
This is finetune version of [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://arxiv.org/abs/2104.08821)
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
| 3 |
|
| 4 |
### Extract sentence representation
|
| 5 |
```
|
|
|
|
| 1 |
This is finetune version of [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://arxiv.org/abs/2104.08821)
|
| 2 |
+
|
| 3 |
+
- Train supervised on 100K triplet samples samples related to stroke domain from : stroke books, quora medical, quora's stroke, quora's general and human annotates.
|
| 4 |
+
- Positive sentences are generated by paraphrasing and back-translate.
|
| 5 |
+
- Negative sentences are randomly selected in general domain.
|
| 6 |
|
| 7 |
### Extract sentence representation
|
| 8 |
```
|