Sentence Similarity
sentence-transformers
Safetensors
English
bert
feature-extraction
Generated from Trainer
dataset_size:56355
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use dat-ai/bge-base-for_text2sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use dat-ai/bge-base-for_text2sql with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("dat-ai/bge-base-for_text2sql") sentences = [ "\n Given the Column informations, generate an SQL query for the following question:\n Column: Finishing position | Points awarded (Platinum) | Points awarded (Gold) | Points awarded (Silver) | Points awarded (Satellite)\n Question: How many platinum points were awarded when 6 gold points were awarded?\n SQL Query: SELECT MAX Points awarded (Platinum) FROM table WHERE Points awarded (Gold) = 6\n ", "How many platinum points were awarded when 6 gold points were awarded?", "Did any team score games that totaled up to 860.5?", "Who had the pole position at the German Grand Prix?" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| [ | |
| { | |
| "idx": 0, | |
| "name": "0", | |
| "path": "", | |
| "type": "sentence_transformers.models.Transformer" | |
| }, | |
| { | |
| "idx": 1, | |
| "name": "1", | |
| "path": "1_Pooling", | |
| "type": "sentence_transformers.models.Pooling" | |
| }, | |
| { | |
| "idx": 2, | |
| "name": "2", | |
| "path": "2_Normalize", | |
| "type": "sentence_transformers.models.Normalize" | |
| } | |
| ] |