Feature Extraction
sentence-transformers
Safetensors
qwen3
sentence-similarity
retrieval
pruned-model
text-embeddings-inference
Instructions to use ukung/semantic-lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use ukung/semantic-lite with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("ukung/semantic-lite") 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
Use English retrieval prompt (nDCG 0.923)
Browse files
config_sentence_transformers.json
CHANGED
|
@@ -7,8 +7,8 @@
|
|
| 7 |
"default_prompt_name": "query",
|
| 8 |
"model_type": "SentenceTransformer",
|
| 9 |
"prompts": {
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
},
|
| 13 |
"similarity_fn_name": "cosine"
|
| 14 |
}
|
|
|
|
| 7 |
"default_prompt_name": "query",
|
| 8 |
"model_type": "SentenceTransformer",
|
| 9 |
"prompts": {
|
| 10 |
+
"query": "Represent this sentence for retrieval:\n",
|
| 11 |
+
"document": "Represent this sentence for retrieval:\n"
|
| 12 |
},
|
| 13 |
"similarity_fn_name": "cosine"
|
| 14 |
}
|