Sentence Similarity
sentence-transformers
ONNX
Safetensors
German
bert
feature-extraction
loss:MatryoshkaLoss
custom_code
text-embeddings-inference
Instructions to use aari1995/German_Semantic_V3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use aari1995/German_Semantic_V3 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("aari1995/German_Semantic_V3", trust_remote_code=True) sentences = [ "Bundeskanzler.", "Angela Merkel.", "Olaf Scholz.", "Tino Chrupalla." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -42,6 +42,8 @@ The successors of [German_Semantic_STS_V2](https://huggingface.co/aari1995/Germa
|
|
| 42 |
|
| 43 |
**Note:** To run this model properly, see "Usage".
|
| 44 |
|
|
|
|
|
|
|
| 45 |
# Major updates and USPs:
|
| 46 |
|
| 47 |
- **Flexibility:** Trained with flexible sequence-length and embedding truncation, flexibility is a core feature of the model. Yet, smaller dimensions bring a minor trade-off in quality.
|
|
|
|
| 42 |
|
| 43 |
**Note:** To run this model properly, see "Usage".
|
| 44 |
|
| 45 |
+
Use this model to create german semantic sentence embeddings.
|
| 46 |
+
|
| 47 |
# Major updates and USPs:
|
| 48 |
|
| 49 |
- **Flexibility:** Trained with flexible sequence-length and embedding truncation, flexibility is a core feature of the model. Yet, smaller dimensions bring a minor trade-off in quality.
|