Sentence Similarity
sentence-transformers
Safetensors
Transformers
bert
feature-extraction
korean
Eval Results (legacy)
text-embeddings-inference
Instructions to use upskyy/e5-small-korean with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use upskyy/e5-small-korean with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("upskyy/e5-small-korean") sentences = [ "이집트 군대가 형제애를 단속하다", "이집트의 군대가 무슬림 형제애를 단속하다", "아르헨티나의 기예르모 코리아와 네덜란드의 마틴 버커크의 또 다른 준결승전도 매력적이다.", "그것이 사실일 수도 있다고 생각하는 것은 재미있다." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use upskyy/e5-small-korean with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("upskyy/e5-small-korean") model = AutoModel.from_pretrained("upskyy/e5-small-korean", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -189,7 +189,7 @@ model-index:
|
|
| 189 |
name: Spearman Max
|
| 190 |
---
|
| 191 |
|
| 192 |
-
#
|
| 193 |
|
| 194 |
This model is korsts and kornli finetuning model from [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
| 195 |
|
|
|
|
| 189 |
name: Spearman Max
|
| 190 |
---
|
| 191 |
|
| 192 |
+
# upskyy/e5-small-korean
|
| 193 |
|
| 194 |
This model is korsts and kornli finetuning model from [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
| 195 |
|