Sentence Similarity
sentence-transformers
PyTorch
Transformers
Korean
bert
feature-extraction
TAACO
text-embeddings-inference
Instructions to use KDHyun08/TAACO_STS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use KDHyun08/TAACO_STS with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("KDHyun08/TAACO_STS") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Transformers
How to use KDHyun08/TAACO_STS with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("KDHyun08/TAACO_STS") model = AutoModel.from_pretrained("KDHyun08/TAACO_STS") - Notebooks
- Google Colab
- Kaggle
Upload with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -2,39 +2,36 @@
|
|
| 2 |
pipeline_tag: sentence-similarity
|
| 3 |
tags:
|
| 4 |
- sentence-transformers
|
| 5 |
-
- feature-extraction
|
| 6 |
- sentence-similarity
|
| 7 |
- transformers
|
| 8 |
-
lan:
|
| 9 |
---
|
| 10 |
|
| 11 |
# TAACO_Similarity
|
| 12 |
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
<!--- Describe your model here -->
|
| 16 |
|
| 17 |
## Usage (Sentence-Transformers)
|
| 18 |
|
| 19 |
-
|
| 20 |
|
| 21 |
```
|
| 22 |
pip install -U sentence-transformers
|
| 23 |
```
|
| 24 |
|
| 25 |
-
|
| 26 |
|
| 27 |
```python
|
| 28 |
from sentence_transformers import SentenceTransformer
|
| 29 |
sentences = ["This is an example sentence", "Each sentence is converted"]
|
| 30 |
|
| 31 |
-
model = SentenceTransformer(
|
| 32 |
embeddings = model.encode(sentences)
|
| 33 |
print(embeddings)
|
| 34 |
```
|
| 35 |
|
| 36 |
|
| 37 |
-
|
| 38 |
## Usage (์ค์ ๋ฌธ์ฅ ๊ฐ ์ ์ฌ๋ ๋น๊ต)
|
| 39 |
Sentence-transformers [sentence-transformers](https://www.SBERT.net) ๋ฅผ ์ค์นํ ํ ์๋ ๋ด์ฉ๊ณผ ๊ฐ์ด ๋ฌธ์ฅ ๊ฐ ์ ์ฌ๋๋ฅผ ๋น๊ตํ ์ ์์ต๋๋ค.
|
| 40 |
query ๋ณ์๋ ๋น๊ต ๊ธฐ์ค์ด ๋๋ ๋ฌธ์ฅ(Source Sentence)์ด๊ณ ๋น๊ต๋ฅผ ์งํํ ๋ฌธ์ฅ์ docs์ list ํ์์ผ๋ก ๊ตฌ์ฑํ์๋ฉด ๋ฉ๋๋ค.
|
|
@@ -72,6 +69,7 @@ for i, (score, idx) in enumerate(zip(top_results[0], top_results[1])):
|
|
| 72 |
|
| 73 |
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
|
| 74 |
|
|
|
|
| 75 |
|
| 76 |
## Training
|
| 77 |
The model was trained with the parameters:
|
|
|
|
| 2 |
pipeline_tag: sentence-similarity
|
| 3 |
tags:
|
| 4 |
- sentence-transformers
|
|
|
|
| 5 |
- sentence-similarity
|
| 6 |
- transformers
|
| 7 |
+
lan: Korean
|
| 8 |
---
|
| 9 |
|
| 10 |
# TAACO_Similarity
|
| 11 |
|
| 12 |
+
๋ณธ ๋ชจ๋ธ์ Sentence-transformers[sentence-transformers](https://www.SBERT.net)๋ฅผ ๊ธฐ๋ฐ์ผ๋ก ํ๋ฉฐ KLUE์ STS(Sentence Textual Similarity) ๋ฐ์ดํฐ์
์ ํตํด ํ๋ จ์ ์งํํ ๋ชจ๋ธ์
๋๋ค. ํ์๊ฐ ์ ์ํ๊ณ ์๋ ํ๊ตญ์ด ๋ฌธ์ฅ๊ฐ ๊ฒฐ์์ฑ
|
| 13 |
+
์ธก์ ๋๊ตฌ์ธ K-TAACO(๊ฐ์ )์ ์งํ ์ค ํ๋์ธ ๋ฌธ์ฅ ๊ฐ ์๋ฏธ์ ๊ฒฐ์์ฑ์ ์ธก์ ํ๊ธฐ ์ํด ์ ์ํ์์ต๋๋ค. ๋ํ ๋ชจ๋์ ๋ง๋ญ์น์ ๋ฌธ์ฅ๊ฐ ์ ์ฌ๋ ๋ฐ์ดํฐ์
์ ํตํด์๋ ํ๋ จ์ ์งํํ ์์ ์
๋๋ค.
|
|
|
|
| 14 |
|
| 15 |
## Usage (Sentence-Transformers)
|
| 16 |
|
| 17 |
+
๋ณธ ๋ชจ๋ธ์ ์ฌ์ฉํ๊ธฐ ์ํด์๋ Sentence-Transformer [sentence-transformers](https://www.SBERT.net)๋ฅผ ์ค์นํ์ฌ์ผ ํฉ๋๋ค.
|
| 18 |
|
| 19 |
```
|
| 20 |
pip install -U sentence-transformers
|
| 21 |
```
|
| 22 |
|
| 23 |
+
๋ชจ๋ธ์ ์ฌ์ฉํ๊ธฐ ์ํด์๋ ์๋ ์ฝ๋๋ฅผ ์ฐธ์กฐํ์๊ธธ ๋ฐ๋๋๋ค.
|
| 24 |
|
| 25 |
```python
|
| 26 |
from sentence_transformers import SentenceTransformer
|
| 27 |
sentences = ["This is an example sentence", "Each sentence is converted"]
|
| 28 |
|
| 29 |
+
model = SentenceTransformer("KDHyun08/TAACO_STS")
|
| 30 |
embeddings = model.encode(sentences)
|
| 31 |
print(embeddings)
|
| 32 |
```
|
| 33 |
|
| 34 |
|
|
|
|
| 35 |
## Usage (์ค์ ๋ฌธ์ฅ ๊ฐ ์ ์ฌ๋ ๋น๊ต)
|
| 36 |
Sentence-transformers [sentence-transformers](https://www.SBERT.net) ๋ฅผ ์ค์นํ ํ ์๋ ๋ด์ฉ๊ณผ ๊ฐ์ด ๋ฌธ์ฅ ๊ฐ ์ ์ฌ๋๋ฅผ ๋น๊ตํ ์ ์์ต๋๋ค.
|
| 37 |
query ๋ณ์๋ ๋น๊ต ๊ธฐ์ค์ด ๋๋ ๋ฌธ์ฅ(Source Sentence)์ด๊ณ ๋น๊ต๋ฅผ ์งํํ ๋ฌธ์ฅ์ docs์ list ํ์์ผ๋ก ๊ตฌ์ฑํ์๋ฉด ๋ฉ๋๋ค.
|
|
|
|
| 69 |
|
| 70 |
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
|
| 71 |
|
| 72 |
+
๋ฌธ์ฅ ๊ฐ ์ ์ฌ๋๋ 1์ด ์ต๋๊ฐ์ด๋ฉฐ, 0์ ๊ฐ๊น์ธ์๋ก ์๋ฏธ์ ์ผ๋ก ์ ์ฌํ์ง ์์ ๋ฌธ์ฅ์
๋๋ค.
|
| 73 |
|
| 74 |
## Training
|
| 75 |
The model was trained with the parameters:
|