Edit model card

A capable language model for text to SQL generation for Postgres, Redshift and Snowflake that is on-par with the most capable generalist frontier models.

image/png

Model Description

Developed by: Defog, Inc Model type: [Text to SQL] License: [CC-by-SA-4.0] Finetuned from model: [Meta-Llama-3-8B-Instruct]

Demo Page

https://defog.ai/sqlcoder-demo/

Ideal prompt and inference parameters

Set temperature to 0, and do not do sampling.

Prompt

<|begin_of_text|><|start_header_id|>user<|end_header_id|>

Generate a SQL query to answer this question: `{user_question}`
{instructions}

DDL statements:
{create_table_statements}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

The following SQL query best answers the question `{user_question}`:
```sql

Evaluation

This model was evaluated on SQL-Eval, a PostgreSQL based evaluation framework developed by Defog for testing and alignment of model capabilities.

You can read more about the methodology behind SQLEval here.

Contact

Contact us on X at @defogdata, or on email at founders@defog.ai

Downloads last month
68,746
Safetensors
Model size
8.03B params
Tensor type
BF16
Β·
Inference API
Input a message to start chatting with defog/llama-3-sqlcoder-8b.

Model tree for defog/llama-3-sqlcoder-8b

Adapters
54 models
Finetunes
13 models
Merges
12 models
Quantizations
9 models

Spaces using defog/llama-3-sqlcoder-8b 12