Sentence Similarity
sentence-transformers
Safetensors
mpnet
feature-extraction
Generated from Trainer
dataset_size:300000
loss:CoSENTLoss
text-embeddings-inference
Instructions to use s2593817/sft-sql-embedding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use s2593817/sft-sql-embedding with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("s2593817/sft-sql-embedding") sentences = [ "SELECT DISTINCT count(alias3.col1) , alias1.col2 FROM table1 AS alias1 JOIN table2 AS alias2 ON alias1.col2 = alias2.col2 JOIN table3 AS alias3 ON alias1.col1 = alias3.col1 WHERE alias2.col3 = str AND alias3.year = num GROUP BY alias1.col2", "SELECT col1 , avg(col2) FROM table1 WHERE col3 LIKE str GROUP BY col1", "SELECT col1 , col2 FROM table1 WHERE col3 LIKE str GROUP BY col1 ORDER BY count(*) DESC LIMIT num", "SELECT col1 , avg(col2) FROM table1 GROUP BY col1 ORDER BY avg(col2)" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Inference
- Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "models/sft-sql-embedding", | |
| "architectures": [ | |
| "MPNetModel" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "mpnet", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "relative_attention_num_buckets": 32, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.41.2", | |
| "vocab_size": 30527 | |
| } | |