RaduGabriel/BGE-M3-SQL

SentenceTransformer

This is a finetuned version of bge-m3 for the task of SQL table retrieval and ranking. <img src="https://cdn-uploads.huggingface.co/production/uploads/65cbd93c19683f98170c8d50/Y5GGGVC3RX0AUzA7oOmAe.png" width="800" height="800">

Model Details

This model can be used to identify relevant SQL tables for query to SQL translation.

The model was finetuned using a curated dataset of SQL table definitions and corresponding natural language queries. The script used for finetuning: Flag Embeddings

Model Description

• —Model Type: Sentence Transformer <!-- - Base model: Unknown -->
• —Maximum Sequence Length: 8192 tokens
• —Output Dimensionality: 1024 tokens
• —Similarity Function: Cosine Similarity <!-- - Training Dataset: Unknown --> <!-- - Language: Unknown --> <!-- - License: Unknown -->

Model Sources

• —Documentation: Sentence Transformers Documentation
• —Repository: Sentence Transformers on GitHub
• —Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'What is the total biomass of fish in farms with a water temperature above 25 degrees Celsius?',
    'CREATE TABLE Farm (FarmID INT, FarmName VARCHAR(50), WaterTemperature DECIMAL, Biomass DECIMAL)',
    'CREATE TABLE Locations (id INT PRIMARY KEY, name VARCHAR(50), region VARCHAR(50), depth INT)',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

<!--

Direct Usage (Transformers)

<details><summary>Click to see the direct usage in Transformers</summary>

</details> -->

<!--

Downstream Usage (Sentence Transformers)

You can finetune this model on your own dataset.

<details><summary>Click to expand</summary>

</details> -->

<!--

Out-of-Scope Use

List how the model may foreseeably be misused and address what users ought not to do with the model. -->

<!--

Bias, Risks and Limitations

What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. -->

<!--

Recommendations

What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. -->

Training Details

Framework Versions

• —Python: 3.10.14
• —Sentence Transformers: 3.0.1
• —Transformers: 4.42.3
• —PyTorch: 2.3.1+cu121
• —Accelerate: 0.31.0
• —Datasets: 2.20.0
• —Tokenizers: 0.19.1

Citation

BibTeX

<!--

Glossary

Clearly define terms in order to be accessible across audiences. -->

<!--

Model Card Authors

Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. -->

<!--

Model Card Contact

Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->