Sentence Similarity
sentence-transformers
Vietnamese
English
deepx-embedding
feature-extraction
embedding
retrieval
vietnamese
legal
linear-attention
gated-deltanet
matryoshka
Eval Results (legacy)
Instructions to use dxtech-asia/deepx-embedding-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use dxtech-asia/deepx-embedding-v1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("dxtech-asia/deepx-embedding-v1") 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] - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -37,7 +37,7 @@ model-index:
|
|
| 37 |
|
| 38 |
**Vietnamese Legal Document Retrieval β State-of-the-Art**
|
| 39 |
|
| 40 |
-
π [dxtech.
|
| 41 |
|
| 42 |
DeepX Embedding v1.0 is a 772M parameter embedding model optimized for Vietnamese legal document retrieval. It achieves nDCG@10 = 0.8162 on the Zalo Legal Text Retrieval benchmark, surpassing the previous SOTA (0.7813) by +4.5%.
|
| 43 |
|
|
|
|
| 37 |
|
| 38 |
**Vietnamese Legal Document Retrieval β State-of-the-Art**
|
| 39 |
|
| 40 |
+
π [dxtech.jp](https://dxtech.jp/deepx-embedding-v1-0-setting-a-new-sota-in-vietnamese-legal-retrieval/) | π [Technical Report](technical_report.html) | π» [GitHub](https://github.com/tungns2408/deepx-embedding-model)
|
| 41 |
|
| 42 |
DeepX Embedding v1.0 is a 772M parameter embedding model optimized for Vietnamese legal document retrieval. It achieves nDCG@10 = 0.8162 on the Zalo Legal Text Retrieval benchmark, surpassing the previous SOTA (0.7813) by +4.5%.
|
| 43 |
|